CN113669626B - Two-stage monitoring method and system for long-distance gas pipeline network - Google Patents
Two-stage monitoring method and system for long-distance gas pipeline network Download PDFInfo
- Publication number
- CN113669626B CN113669626B CN202110900790.9A CN202110900790A CN113669626B CN 113669626 B CN113669626 B CN 113669626B CN 202110900790 A CN202110900790 A CN 202110900790A CN 113669626 B CN113669626 B CN 113669626B
- Authority
- CN
- China
- Prior art keywords
- data
- simulation
- monitoring
- long
- gas pipeline
- 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
Images
Classifications
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F17—STORING OR DISTRIBUTING GASES OR LIQUIDS
- F17D—PIPE-LINE SYSTEMS; PIPE-LINES
- F17D1/00—Pipe-line systems
- F17D1/02—Pipe-line systems for gases or vapours
- F17D1/04—Pipe-line systems for gases or vapours for distribution of gas
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F17—STORING OR DISTRIBUTING GASES OR LIQUIDS
- F17D—PIPE-LINE SYSTEMS; PIPE-LINES
- F17D3/00—Arrangements for supervising or controlling working operations
- F17D3/01—Arrangements for supervising or controlling working operations for controlling, signalling, or supervising the conveyance of a product
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F17—STORING OR DISTRIBUTING GASES OR LIQUIDS
- F17D—PIPE-LINE SYSTEMS; PIPE-LINES
- F17D5/00—Protection or supervision of installations
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]
Abstract
The invention relates to a two-stage monitoring method and a two-stage monitoring system for a long-distance gas pipeline network, wherein the method involves the steps of storing prepositive data in key points; and performing primary monitoring based on the pre-data stored in the key points, and performing secondary monitoring by the control module based on the collected monitoring data when monitoring abnormality is found. According to the invention, the monitoring is carried out at the key points of the long-distance gas pipeline network in a mode of combining simulation and actual data, and the sensor device is arranged to reduce the monitoring difficulty and the cost of the long-distance gas pipeline network in a two-stage monitoring mode.
Description
[ field of technology ]
The invention belongs to the field of long-distance gas pipeline networks, and particularly relates to a two-stage monitoring method and system for a long-distance gas pipeline network.
[ background Art ]
Along with the improvement of environmental protection consciousness of the whole society, the development and utilization of green energy are increasingly receiving attention of people. The fuel gas is used as a clean energy source which is green, environment-friendly, economical, safe and reliable, has good effect on improving the natural environment of human beings, has attracted great attention to society, and the government of China is also greatly pushing the coal-to-gas engineering. The gas pipe network can be divided into a long-distance gas pipe network, a city gas pipe network and an industrial enterprise gas pipe network according to the purposes. The fuel gas from the gas source is typically passed through a long pipeline network, a municipal fuel gas network or an industrial fuel gas network to finally reach the user. Once leakage occurs, if the treatment measures are reasonable and proper, the gas can be safely discharged, and only small economic loss is caused. Leakage refers to the loss of undesired fluid flow out of a container or pipe network. Along with the transportation of urban gas pipe network, the main factors that cause gas pipe network leakage include: design defects, materials and construction defects, corrosion factors, natural factors, human activities, improper operation and maintenance, human damage, and the like.
The detection and positioning of urban gas pipe network leakage are one of measures for preventing disasters, and whether gas leaks or not can be timely found through accurate positioning and real-time detection, so that measures are timely taken to prevent disaster accidents from being in a sprouted state, and therefore a great deal of researches are carried out on monitoring and detection of gas pipe networks by students at home and abroad. However, most researches are based on data calculation or big data calculation, and the data and products in the whole design, simulation, test and actual use process of the whole gas pipe network are not fully utilized; according to the invention, the monitoring is carried out at the key points of the long-distance gas pipeline network in a mode of combining simulation and actual data, and the sensor device is arranged to reduce the monitoring difficulty and the cost of the long-distance gas pipeline network in a two-stage monitoring mode; specifically, (1) redundant monitoring data based on a clustering center is obtained based on test data, and effective primary data monitoring is supported; (2) The error function is obtained through the comparison of the simulation data and the test data, and the calculation of the error is supported, so that the quick primary monitoring by using the clustering center and the error can be realized; (3) The proportion of the actual operation data and the simulation data is adjusted, so that the front-end data can represent the actual operation condition of the pipe network structure more accurately, and the self-adaptation of front-end monitoring is realized; (4) Clustering is introduced in the selection of the prepositive data, the prepositive data is selected according to the data density, and the rapid data judgment is realized to realize rapid monitoring; in addition, the invention improves the monitoring efficiency through the local and remote quick comparison, and reduces the inundation effect of the conventional data on important data, thereby improving the monitoring sensitivity.
[ invention ]
In order to solve the problems in the prior art, the invention provides a two-stage monitoring method and a two-stage monitoring system for a long-distance gas pipeline network.
The technical scheme adopted by the invention is as follows:
step S1: designing and obtaining a long-distance gas pipeline network structure and a simulation model thereof; acquiring prepositive data prepositioned into the key points through testing and simulation;
step S2: storing the prepositive data in the key points; and performing primary monitoring based on the pre-data stored in the key points, and performing secondary monitoring by the control module based on the collected monitoring data when monitoring abnormality is found.
Further, the long-distance gas pipeline network structure is designed according to design experience and working condition requirements.
Further, the preamble data includes a fixed portion and a movable portion.
Further, the preamble data is stored in the monitoring device at the key point.
Further, the control module is not located at the cloud; all test data and simulation data from different keypoints are saved as big data.
A long gas pipeline network two-stage monitoring system, comprising: the control module is connected with other modules and is used for reading the monitoring data, carrying out subsequent processing, data communication and the like;
the data acquisition module is used for acquiring monitoring data of the gas pipe network from the sensor and sending the acquired monitoring data to the control module;
the monitoring device is arranged at a key point of the gas pipe network and is used for acquiring monitoring data;
the long-distance gas pipeline network two-stage monitoring system is used for the method.
Further, the monitoring device is a sensor.
Further, the key points are selected empirically.
Further, the monitoring device has a locally limited memory space.
Further, the monitoring device is capable of monitoring one or more types of monitoring data.
The beneficial effects of the invention are as follows: monitoring is carried out at key points of the long-distance gas pipeline network in a mode of combining simulation and actual data, and a sensing device is arranged to reduce the monitoring difficulty and the cost of the long-distance gas pipeline network in a two-stage monitoring mode; specifically, (1) redundant monitoring data based on a clustering center is obtained based on test data, and effective primary data monitoring is supported; (2) The error function is obtained through the comparison of the simulation data and the test data, and the calculation of the error is supported, so that the quick primary monitoring by using the clustering center and the error can be realized; (3) The proportion of the actual operation data and the simulation data is adjusted, so that the front-end data can represent the actual operation condition of the pipe network structure more accurately, and the self-adaptation of front-end monitoring is realized; (4) Clustering is introduced in the selection of the prepositive data, the prepositive data is selected according to the data density, and the rapid data judgment is realized to realize rapid monitoring; in addition, the invention improves the monitoring efficiency through local quick comparison, and reduces the inundation effect of the conventional data on important data, thereby improving the monitoring sensitivity.
[ description of the drawings ]
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this application, illustrate and together with the description serve to explain the invention, if necessary:
FIG. 1 is a schematic diagram of a two-stage monitoring method of a long gas pipeline network of the invention.
[ detailed description ] of the invention
The present invention will now be described in detail with reference to the drawings and the specific embodiments thereof, wherein the exemplary embodiments and the description are for the purpose of illustrating the invention only and are not to be construed as limiting the invention.
The invention relates to a two-stage monitoring system of a long-distance gas pipeline network, which comprises the following components:
the control module is connected with other modules and is used for reading the monitoring data, carrying out subsequent processing, data communication and the like;
the data acquisition module is used for acquiring monitoring data of the gas pipe network from the sensor and sending the acquired monitoring data to the control module;
the sensor is arranged at a key point of the gas pipe network and used for acquiring a monitoring value; the key points are selected according to experience; the simulation data can be selected and set according to the change of the simulation data; the sensor has a locally limited storage space and can store a small amount of data;
preferably: the sensor is connected with the data acquisition module in a wireless or wired mode;
preferably: the sensor is one or more types and is used for acquiring one or more types of detection and monitoring data; for example: temperature, sound, pressure, etc.;
the power supply module is used for supplying power to each module in the system;
the display module is used for displaying information on the LCD display and realizing man-machine interaction function;
the storage module is used for storing and acquiring data;
based on the two-stage monitoring system of the long-distance gas pipeline network, the two-stage monitoring method of the long-distance gas pipeline network specifically comprises the following steps:
step 100, designing and acquiring a long-distance gas pipeline network structure and a simulation model thereof, and testing the long-distance gas pipeline network structure to acquire a fixed part in front data; the preposed data are data which are preposed to key points and used for primary monitoring; the fixed part is a corresponding test result or simulation result obtained according to the test or simulation, and the fixed part is kept unchanged and can be stored in a fixed storage device;
the step 100 specifically includes the following steps:
step S101: designing a long-distance gas transmission pipe network structure; specific: designing a long-distance gas pipeline network structure according to design experience and working condition requirements;
step S102: obtaining long-distance gas pipeline network structure test data in a test stage; specific: after the construction of the long-distance gas pipeline network structure is finished, entering a testing stage, and acquiring testing data in the actual operation process; the working condition of the test stage is similar to the working condition of the actual operation of the later stage, so that the test result obtained by the test data is similar;
step S103: establishing a simulation model of the long-distance gas pipeline network structure, and acquiring simulation data based on the simulation model; setting up working conditions in a test stage to simulate so as to obtain simulation data;
step S104: judging whether the test data and the simulation data meet the consistency condition, and if so, acquiring the front data based on the simulation data and the test data; if not, the artificial feedback is carried out to check whether the pipe network structure has field problems, and the long-distance gas transmission pipe network structure is adjusted based on the artificial feedback result; usually, people are completely separated from the test after the simulation model is built, because the construction time of the long-distance pipeline network is long, but the monitoring efficiency can be improved as long as the analysis and the utilization of the data can be kept;
according to the Gelebus criterion, the overall distribution of the data presents normal distribution, and abnormal data can be found through residual values; according to the invention, the test data and the simulation data are mixed into a whole, if the consistency is met between the test data and the simulation data, the number of the data regarded as abnormal data is limited, the data inhibition judgment is carried out according to the criterion, when the value of n is large enough, the inconsistency is still presented, the test and the simulation are obviously deviated, and the obvious problem that the pipe network laying structure is not easy to find possibly exists; on-site diagnosis is required; thereby avoiding the large data volume and the calculation time required by data fitting and improving the judging efficiency of the monitoring data;
the step of judging whether the test data and the simulation data meet the consistency condition comprises the following steps: acquiring n test data D 1 …D i …D n And n simulation data SD corresponding thereto n+1 …SD n+i …SD n+n Put into the global set { ZD } j In the process of }, the data average value of the whole set is calculated
Calculating data residual +.>
Judging that the residual error |delta j| > g (n, a) x sigma (ZD) is satisfied j ) If the number of the data which is satisfied exceeds a preset value, determining that the consistency condition is satisfied, otherwise, determining that the consistency condition is not satisfied; wherein: a is a significant level, n is the number of tests, g (n, a) is a table look-up coefficient;
preferably: a is set to 0.01; />
The method for acquiring the front data based on the simulation data and the test data comprises the following steps: comparing the simulation data with the test data to obtain a fixed error of the structure; fitting the simulation data and the fixed errors to obtain a fixed error fitting curve, and storing the fixed error fitting curve; taking the fixed error fitting curve as a fixed part in the preposed data; of course the number of tests required here is sufficient, if possible, requiring multiple tests under different types, performing a splice of the fitted curves and eventually forming a fixed part;
step 200: acquiring an active part in the front data according to the simulation model; the method specifically comprises the following steps:
step S201: inputting the test working condition data into a simulation model to obtain simulation data; wherein: the test condition data is from a test sample;
alternatively, the following is used: along with the long-term use of the gas pipe network structure, in the actual use process, inputting actual working condition data into a simulation model to obtain simulation data, and giving the simulation data to obtain an active part in the front data;
alternatively, the following is used: along with the long-term use of the gas pipe network structure, after the use time reaches a time threshold, merging actual data and simulation data, and acquiring an active part in the front data based on a merging set of the actual data and the simulation data; wherein: the merging mode is that the proportion of actual data in a merging set is continuously increased along with the increase of the using time until the preset proportion is reached;
preferably: deleting the simulation data in the first N1 clusters with the largest simulation data in the simulation data, and replacing the simulation data with actual data, thereby increasing the number of the actual data in the merging set; the large quantity of the simulation data in the clusters often indicates that the simulation data corresponds to conventional working condition data, the working condition data can be automatically increased along with the increase of the actual running time, and in cooperation with the conventional working condition data, the monitoring data of the pipe network structure can be stabilized along with the continuous use of the pipe network structure, the simulation data does not play a role in guiding any more, so that the pre-arranged active data in the subsequent clusters can represent the actual running condition of the pipe network to a great extent, and a more accurate monitoring role can be played;
step S202: calculating a clustering result of the simulation data; after clustering, the density of data outside the clusters is lower than that of data in the clusters; at this time, at least a first quantity of simulation data needs to be contained in the cluster radius neighborhood of the cluster center so that the density in the cluster radius neighborhood exceeds a density threshold; thus, we convert the pre-selection problem of the simulation data into a clustering problem; although simulation data may have a plurality of discrete values, the pre-processing of the part of data does not increase the monitoring efficiency, and more data can be presented around a clustering center, namely the simulation data distributed more densely, so that clustering is introduced in pre-processing data selection, the pre-processing of the data is selected according to the data density, and rapid data judgment is realized to realize rapid monitoring;
the step S202 specifically includes the following steps:
step S2021: calculating the local density ρ of each simulation data i And a weighted distance WD i ；
Wherein: if d i，j ≤d c F (d) i，j -d c ) =1, otherwise F (d i，j -d c )＝0；d c Is the cut-off distance; d, d i，j Is the data difference between the simulation data i and the simulation data j;
WD i ＝WA i ×(WB×WC i +D)；
WA i ＝min{d i，j ，j∈if(ρ j ＞ρ i )}；
wherein: WA (Wireless LAN area) i Is a weighting coefficient for measuring the variability between different simulated data-centric local densities; WB and D are tuning constants; WC (Wolfram carbide) i Is the simulation data adjustment coefficient; the adjustment coefficient of each simulation data is different, and the different adjustment coefficients are obtained through a density and simulation data quantity lookup table;
preferably: the WB and D settings are related to the amount of simulation data;
step S2022: setting a clustering center of simulation data; the method comprises the following steps: taking simulation data with local density and weighted distance respectively larger than a first preset value and a second preset value as a clustering center; wherein: the first preset value and the second preset value are set in advance according to the number of key points and the storage capacity of the sensor;
step S2023: dividing simulation data of a non-clustering center into clusters; the method comprises the following steps: calculating the distance between each simulation data and each cluster center, and dividing the simulation data into clusters where the closest cluster centers are located; taking the simulation data which cannot be classified as discrete values and not classifying any clusters; the discrete values in the two-stage arrangement are not available for one-stage monitoring, i.e. the preamble, and are only useful in two-stage monitoring of big data;
step S2024: outputting a clustering result; the method comprises the following steps: outputting a cluster center and a cluster corresponding to the cluster center;
step S203: taking simulation data corresponding to the cluster centers of the first n clusters with the largest simulation data in the clusters in the clustering result as an active part in the preposed data; the data of the movable part is dynamically changed along with the increase of the data quantity;
preferably: the activity part value comprises simulation data corresponding to a clustering center;
step 300: storing the fixed part and the movable part in the preposed data in key points; all the test data and simulation data are stored in the control module;
preferably: the fixed part is kept unchanged, and the movable part is dynamically changed along with the actual working condition of the long-distance gas pipeline network structure;
preferably: the proportion of the actual operation data and the simulation data is adjusted, so that the front-end data can represent the actual operation condition of the pipe network structure more accurately, and the self-adaptation of front-end monitoring is realized; along with the use of the gas pipe network structure, each performance of the gas pipe network structure is gradually stable, actual use data is gradually increased, after the use time reaches a time threshold, the actual data and the simulation data are combined, and an active part in the front data is acquired based on the combined set of the actual data and the simulation data; i.e. step S202 is performed based on the merged set; the merging mode is to continuously increase the proportion of the actual data in the merging set along with the use time until the preset proportion is reached; wherein: the preset proportion is set in advance;
preferably: the preset proportion is 80%; the rest 20% of data are simulation data representing special working conditions;
that is, for a key point, only n pieces of simulation data need to be stored in the monitoring device, so that the requirement on the storage space is very small, and the common sensor can meet the requirement;
preferably: the control module is not located at the cloud; all the test data and simulation data from different key points are stored in the cloud as big data;
step 400: monitoring based on the pre-data stored in the key points, and when monitoring abnormality is found, performing secondary monitoring by the control module based on the collected monitoring data; that is, in the case of normal operation or only in the case of a change in the industrial and mining industry, and in accordance with the simulation data display and within the error allowable range, the key point self-monitoring does not emit monitoring abnormality; otherwise, the control module carries out secondary monitoring and research and judgment based on big data;
the monitoring is performed based on the prepositive data stored in the key points, specifically: after the fixed part of the front data acts on the activity data of the front part, comparing the activity data with the real-time monitoring data to determine whether monitoring abnormality occurs; when the two are obviously deviated, determining that abnormality occurs to carry out secondary monitoring;
the control module carries out secondary monitoring based on the collected monitoring data, and specifically comprises the following steps: comparing the collected monitoring data with complete simulation data and/or big data monitoring data to determine whether monitoring abnormality occurs;
under the general condition, the simulation is complete, the simulation data basically spans all actual working conditions, and whether the deviation of the current monitoring data is caused by the actual working conditions or the abnormality is caused by the fact can be determined by comparing the current monitoring data with the complete simulation data;
under the condition that the number of key points is large, the sensors arranged at each key point, even the sensors surrounding the MCU, can be automatically monitored, the front part in the two-stage monitoring can be continuously close to the real working condition, the error range is overcome, and an effective and efficient two-stage monitoring mechanism is formed;
because the characteristics of different sensing devices are different, the devices at each key point can perform necessary data conversion to increase the automatic processing capacity of the front part of the sensing devices, and the key point for monitoring is not required to be set up in all places of the gas pipe network structure, namely the place which is required to be emphasized by the invention, and only the monitoring node is required to be set at the key position, so that the cost can be greatly saved. Then, enabling the sensing equipment at the key point position to be connected with the control module;
of course, instructions to set the privilege level are required to cause the control module to execute in time on the information sent by the user. Once an abnormality occurs in the gas pipe network structure, it is necessary to cut off the connection of the abnormal part in the structure immediately so as not to cause unnecessary losses in all aspects.
When the control module is located at the cloud end, the cloud end server continuously receives various data from the key points, and the cloud end classifies and analyzes the various data, so that the system and the secondary monitoring capacity are continuously optimized;
the foregoing description is only of the preferred embodiments of the invention, and all changes and modifications that come within the meaning and range of equivalency of the structures, features and principles of the invention are therefore intended to be embraced therein.
Claims (1)
1. The two-stage monitoring method for the long-distance gas pipeline network is characterized by comprising the following steps of:
step S100: designing and obtaining a long-distance gas pipeline network structure and a simulation model thereof; acquiring prepositive data prepositioned into the key points through testing and simulation; specific: designing and acquiring a long-distance gas pipeline network structure and a simulation model thereof, and testing the long-distance gas pipeline network structure to acquire a fixed part in the front data; the preposed data are data which are preposed to key points and used for primary monitoring; the fixed part is a corresponding test result or simulation result obtained according to the test or simulation, and the fixed part is kept unchanged;
the step S100 specifically includes the following steps:
step S101: designing a long-distance gas transmission pipe network structure; specific: designing a long-distance gas pipeline network structure according to design experience and working condition requirements;
step S102: obtaining long-distance gas pipeline network structure test data in a test stage; specific: after the construction of the long-distance gas pipeline network structure is finished, entering a testing stage, and acquiring testing data in the actual operation process;
step S103: establishing a simulation model of the long-distance gas pipeline network structure, and acquiring simulation data based on the simulation model; setting up working conditions in a test stage to simulate so as to obtain simulation data;
step S104: judging whether the test data and the simulation data meet the consistency condition, and if so, acquiring the front data based on the simulation data and the test data; if not, the artificial feedback is carried out to check whether the pipe network structure has field problems, and the long-distance gas transmission pipe network structure is adjusted based on the artificial feedback result;
the method for acquiring the front data based on the simulation data and the test data comprises the following steps: comparing the simulation data with the test data to obtain a fixed error of the structure; fitting the simulation data and the fixed errors to obtain a fixed error fitting curve, and storing the fixed error fitting curve; taking the fixed error fitting curve as a fixed part in the preposed data;
step 200: acquiring an active part in the front data according to the simulation model; the method specifically comprises the following steps:
step S201: inputting the test working condition data into a simulation model to obtain simulation data; along with the long-term use of the gas pipe network structure, after the use time reaches a time threshold, merging actual data and simulation data, and acquiring an active part in the front data based on a merging set of the actual data and the simulation data; wherein: the merging mode is that the proportion of actual data in a merging set is continuously increased along with the increase of the using time until the preset proportion is reached;
step S202: calculating a clustering result of the simulation data; after clustering, the density of data outside the clusters is lower than that of data in the clusters;
step S203: taking simulation data corresponding to the cluster centers of the first n clusters with the largest simulation data in the clusters in the clustering result as an active part in the preposed data; the data of the movable part is dynamically changed along with the increase of the data quantity;
step 300: storing the fixed part and the movable part in the preposed data in key points; all the test data and simulation data are stored in the control module;
step 400: and monitoring based on the pre-data stored in the key points, and when monitoring abnormality is found, performing secondary monitoring based on the collected monitoring data by the control module.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110900790.9A CN113669626B (en) | 2021-08-06 | 2021-08-06 | Two-stage monitoring method and system for long-distance gas pipeline network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110900790.9A CN113669626B (en) | 2021-08-06 | 2021-08-06 | Two-stage monitoring method and system for long-distance gas pipeline network |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113669626A CN113669626A (en) | 2021-11-19 |
| CN113669626B true CN113669626B (en) | 2023-05-09 |
Family
ID=78541690
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110900790.9A Active CN113669626B (en) | 2021-08-06 | 2021-08-06 | Two-stage monitoring method and system for long-distance gas pipeline network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113669626B (en) |
Family Cites Families (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7539597B2 (en) * | 2001-04-10 | 2009-05-26 | Smartsignal Corporation | Diagnostic systems and methods for predictive condition monitoring |
| CN101093058A (en) * | 2007-06-28 | 2007-12-26 | 天津大学 | System and method for automatic monitoring pipeline network of fuel gas in city |
| CN103939749B (en) * | 2014-04-28 | 2016-08-24 | 东北大学 | Flow circuits based on big data leakage intelligent adaptive monitoring system and method |
| CN106877383B (en) * | 2015-12-11 | 2020-09-11 | 中国电力科学研究院 | Method for adjusting low voltage ride through capability simulation model of variable speed wind turbine generator |
| CN106649877A (en) * | 2017-01-06 | 2017-05-10 | 广东工业大学 | Density peak-based big data mining method and apparatus |
| CN107420743B (en) * | 2017-06-09 | 2023-06-13 | 中国计量大学 | Intelligent urban gas PE pipe network measurement and control system and measurement and control method |
| CN109444728A (en) * | 2018-09-21 | 2019-03-08 | 国网河南省电力公司济源供电公司 | A kind of circuit breaker failure diagnostic method based on dynamic weighting Hybrid Clustering Algorithm |
| CN109458563A (en) * | 2018-10-23 | 2019-03-12 | 青岛理工大学 | A kind of open local water supply network dynamic self-adapting emulation modelling method |
-
2021
- 2021-08-06 CN CN202110900790.9A patent/CN113669626B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN113669626A (en) | 2021-11-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109784746A (en) | Urban-rural water supply network waterpower simulation of water quality platform | |
| CN107831285B (en) | A kind of dystrophication monitoring system and method based on Internet of Things | |
| CN102289590B (en) | Method for estimating operating state of SF6 high-voltage circuit breaker and intelligent system | |
| CN102269972B (en) | Method and device for compensating pipeline pressure missing data based on genetic neural network | |
| CN100492233C (en) | Gas pipe network accidents early warning method | |
| CN102156413B (en) | Emergency scheduling method and system thereof for urban multi-source raw water system | |
| CN102931625B (en) | Online state maintenance intelligent decision analysis device used for relay protection device, and signal processing method and application thereof | |
| CN104008302A (en) | Power distribution network reliability evaluation method based on combinational weighting and fuzzy scoring | |
| CN109254219B (en) | A kind of distribution transforming transfer learning method for diagnosing faults considering multiple factors Situation Evolution | |
| CN112460492A (en) | Toughness-evaluation-based collaborative toughness-enhanced gas safety control device | |
| CN114862169A (en) | BIM-based tunnel engineering safety risk monitoring system and method | |
| CN113669626B (en) | Two-stage monitoring method and system for long-distance gas pipeline network | |
| CN113015120B (en) | Pollution control monitoring system and method based on neural network | |
| CN111552686B (en) | Power data quality assessment method and device | |
| CN113704231A (en) | Building water supply system database construction and query method | |
| CN114593375B (en) | Secondary water supply community pipeline leakage monitoring and positioning method based on pump house energy consumption | |
| CN113944801B (en) | Gas pressure regulator performance detection method and device based on data analysis | |
| CN214674755U (en) | Pipe network monitoring control system based on fluid energy power generation in pipeline | |
| CN115371740B (en) | Detection platform and detection method for environmental protection disposal | |
| CN111022935B (en) | Method, device and system for detecting broken leakage of air pipe network of sewage treatment equipment | |
| CN116743618B (en) | Data acquisition and analysis method, equipment and medium of station remote equipment | |
| CN113449120B (en) | Pipeline safety comprehensive supervision method combining spatial information | |
| CN116989277A (en) | Dynamic water supply network leakage risk assessment method based on Adaboost and BP neural network | |
| Xiang et al. | Application of Kalman filter model in automatic monitoring system of geological hazards | |
| Linjing et al. | Application of secondary water supply water quality evaluation method based on K-means clustering and entropy method |
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 |