CN113357545A - Method and system for diagnosing abnormity of urban complex gas pipe network - Google Patents
Method and system for diagnosing abnormity of urban complex gas pipe network Download PDFInfo
- Publication number
- CN113357545A CN113357545A CN202110547193.2A CN202110547193A CN113357545A CN 113357545 A CN113357545 A CN 113357545A CN 202110547193 A CN202110547193 A CN 202110547193A CN 113357545 A CN113357545 A CN 113357545A
- Authority
- CN
- China
- Prior art keywords
- pipe network
- abnormality
- diagnosis
- network
- diagnosing
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- 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
- F17D5/02—Preventing, monitoring, or locating loss
Abstract
The invention relates to a method and a system for diagnosing the abnormality of an urban complex gas pipe network, wherein the method comprises the following steps: connecting the layout points based on the topological relation of the pipe network to form a layout point relation graph; clustering attribute values of the nodes based on the weight values of the edges in the relational graph to obtain a plurality of classes; performing classification abnormity judgment on the gas network based on the clustering result; and performing abnormality diagnosis based on the classified abnormality determination result. The method and the device perform abnormity diagnosis aiming at the complex urban trachea network, fuse the actual pipe network condition, fuse the real-time detection result, increase the completeness and diversity of input, and are beneficial to abnormity diagnosis of the complex trachea network.
Description
[ technical field ] A method for producing a semiconductor device
The invention belongs to the technical field of energy automation, and particularly relates to a method for diagnosing urban complex tracheal network abnormity.
[ background of the invention ]
Gas energy, such as gas, is one of the most important energy sources in the world today and relies mainly on pipeline transmission. With the improvement of the living standard of people, the demand of urban gas is continuously increased. Meanwhile, gas pipeline leakage is the primary form of gas pipeline failure. The leakage of pipeline gas brings great potential safety hazard, and because the urban buried gas pipe network conveying medium has the dangerous characteristics of explosiveness, flammability and the like, once the conveying medium is failed and damaged, huge economic loss is often caused, even catastrophic accidents are caused, and the life and property safety of the country, enterprises and people can be seriously threatened. Therefore, the method has important significance for accurately positioning the leakage point of the gas pipeline. However, underground pipelines in China are in a trend of increasing day by day, the problem of pipeline safety is more and more emphasized, the existing gas pipeline leakage detection method and equipment have the disadvantages of multiple principles, complex structure, insensitivity in detection, incapability of detecting tiny leakage points, frequent occurrence of false alarm, high input cost, poor information timeliness and easiness in false alarm, and monitoring blind areas exist at positions of joints of pipelines and the like. On one hand, gas such as gas is used as energy supply time in China for decades, aging of gas pipe networks of pipelines, cells, control nodes and the like in cities is greatly inconsistent, so that city pipe networks in many places have high complexity, and the gas pipe networks can not be accurately positioned by adopting a uniform detection means. In the prior art, the possibility of uniform detection or the possibility of detection and equipment arrangement are not considered at all, the method is not suitable for leakage positioning of a complex gas pipe network, and in the complex city pipe network, when the city pipeline is abnormal, how to accurately and timely master the abnormal condition, so that the problem that subsequent accidents are to be solved is solved.
The method is used for carrying out abnormity diagnosis on the complex urban gas pipe network, fusing the actual pipe network condition, fusing the real-time detection result, increasing the completeness and diversity of input, facilitating abnormity diagnosis of the complex gas pipe network, and processing the complex condition, thereby avoiding resource waste and influence on road traffic and safety, and specifically (1) the characteristic of the pipe network which can be represented by detection data to the maximum extent through differentiated selection of layout points and combination of a clustering mode, thereby carrying out subsequent abnormity diagnosis, overcoming the condition that the arrangement cannot be ignored in a special area, utilizing the collectable data to the maximum extent, and improving the accuracy and efficiency of the layout of the complex pipe network; (2) quickly positioning representative core nodes by using the locality of the pipe network layout points, embodying the locality through the core nodes and participating the obvious characteristics embodying the pipe network characteristics into subsequent diagnosis through the weighted edges; (3) the topological structure and the measurement result are combined through the relational graph and the attribute value, and the attribute value is synthesized to diagnose while the actual physical condition is considered, so that the diagnosis of a large-range pipe network becomes possible, and a foundation is laid for accurate diagnosis; (4) the method integrates the actual pipe network condition, integrates the real-time detection result, increases the completeness and diversity of input, and is beneficial to the abnormity diagnosis of the complex gas pipe network.
[ summary of the invention ]
In order to solve the above problems in the prior art, the invention provides an abnormality diagnosis method for an urban complex gas pipe network, which comprises the following steps:
step S1: for each sensor type, differentially selecting layout points on the tracheal net and laying sensors;
step S2: connecting the layout points based on the topological relation of the pipe network to form a layout point relation graph;
step S3: clustering attribute values of the nodes based on the weight values of the edges in the relational graph to obtain a plurality of classes;
step S4: performing classification abnormity judgment on the gas network based on the clustering result;
step S5: and performing abnormality diagnosis based on the classified abnormality determination result.
Further, the step S1 is specifically: the distribution points are uniformly arranged in the tracheal tube segment in the non-special area, and the distribution points are selected in the special area so that the number of the distribution points is not less than the minimum distribution value.
Further, the uniform setting may be selecting a setting point in a given area, or setting the length of the pipe network in a preset area according to a preset length.
Further, the minimum distribution value is a preset value.
Furthermore, when the minimum distribution value cannot be met, the special area is calibrated according to the single data characteristic.
Furthermore, a layout point is selected at the boundary of the special area, and the sensors are arranged at the layout point.
Further, the preset length is 50M.
An abnormality diagnosis device for an urban complex tracheal network, comprising:
a storage unit configured to store an application program; and
a processing unit electrically coupled to an input unit and the storage unit, the processing unit configured to perform the method.
An abnormality diagnosis system for a complex urban tracheal network, comprising: a server and a client;
the client is used for sending an abnormity diagnosis request of the urban complex trachea network to the server;
the server is used for executing the method.
Further, the storage medium for diagnosing the abnormality of the urban complex tracheal network is characterized in that the storage medium is used for storing instructions for executing the method.
The beneficial effects of the invention include: (1) the method has the advantages that the detection data can represent the characteristics of the pipe network to the maximum extent through the differentiated selection of the layout points and the combination of clustering, so that subsequent abnormity diagnosis can be performed, the condition that the layout cannot be ignored in diagnosis in a special area is overcome, the collectable data are utilized to the maximum extent, and the accuracy and the efficiency of the layout of the complex pipe network are improved; (2) quickly positioning representative core nodes by using the locality of the pipe network layout points, embodying the locality through the core nodes and participating the obvious characteristics embodying the pipe network characteristics into subsequent diagnosis through the weighted edges; (3) the topological structure and the measurement result are combined through the relational graph and the attribute value, and the attribute value is synthesized to diagnose while the actual physical condition is considered, so that the diagnosis of a large-range pipe network becomes possible, and a foundation is laid for accurate diagnosis; (4) the method integrates the actual pipe network condition, integrates the real-time detection result, increases the completeness and diversity of input, and is beneficial to the abnormity diagnosis of the complex gas pipe network.
[ 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, and are not to be considered limiting of the invention, in which:
fig. 1 is a schematic diagram of the method for diagnosing the abnormality of the urban complex gas pipe network.
[ detailed description ] embodiments
The present invention will now be described in detail with reference to the drawings and specific embodiments, wherein the exemplary embodiments and descriptions are provided only for the purpose of illustrating the present invention and are not to be construed as limiting the present invention.
Gas such as gas is used as energy supply time in China for decades, and aging of gas pipe networks of pipelines, districts, control nodes and the like in cities is greatly inconsistent, so that city pipe networks in many places have high complexity. The pipe network in some areas does not have installation conditions for pressure sensors or GPS positioning devices and the like, and the leakage amount, the hiding degree and the damage degree caused by leakage of the pipe network with poor conditions are large; in this case, the sensors cannot be arranged according to the requirements of the topological structure of the pipe network, even in an optimized manner, or in a uniform node arrangement manner, and the diagnosis result cannot be obtained based on the arrangement methods;
the method for diagnosing the abnormality of the urban complex gas pipe network comprises the following steps:
step S1: for each sensor type, differentially selecting arrangement points on the tracheal net, and arranging various sensors at the arrangement points; specifically, the method comprises the following steps: uniformly arranging distribution points in the tracheal tube segment in a non-special area, and selecting the distribution points in the special area to ensure that the number of the distribution points is not less than the minimum distribution value;
the complex gas pipe network can not be uniformly distributed obviously, the detection data can represent the characteristics of the pipe network to the maximum extent through the differentiated selection of distribution points and the combination of a clustering mode, so that the subsequent leakage diagnosis can be carried out, the condition that the distribution in a special area can not be ignored by diagnosis is overcome, and the accuracy and the efficiency of the distribution of the complex pipe network are improved;
when the distribution point is selected for a non-special area, the uniform setting can be that a distribution point is selected in a given area (for example, 100M2), or a pipe network in a preset area is segmented according to a preset length (for example, 50M), and a sensor is arranged for each segment; the special and non-special areas are distinguished by differences in the characteristics of the tracheal network, for example: selecting the difficulty of arranging points, the construction age, the application type and the like;
preferably: the minimum distribution value is a preset value and can be set according to information such as the area of a special area, the length of a contained pipe network and the like; the characteristics of the special region can participate in the representation of diagnosis through the limitation of the minimum arrangement value, and scientifically participate in the diagnosis;
preferably: when the minimum arrangement value cannot be met, calibrating a special area according to the single data characteristic, selecting arrangement points at the boundary of the special area, and arranging sensors at the arrangement points;
the calibrating of the special area according to the single data characteristic specifically comprises: calibrating a region within the tracheal network range with a single characteristic value as a specific region through a single data characteristic; for example: the single characteristics comprise the difficulty of arranging the sensors, the construction age, the application type, the pipe network attribute and the like; the value of an intentional characteristic may be defined by information such as a range; such as the laying age is earlier than 1980;
preferably: calibrating distribution points at the boundary of the special area in a manual calibration mode;
step S2: connecting the layout points based on the topological relation of the pipe network to form a layout point relation graph; specifically, the method comprises the following steps: taking the distribution points as nodes in the relational graph, and setting edges between the two distribution points when the two distribution points are directly communicated in the topological relation of the pipe network and do not pass through other distribution points; the attribute value of the layout point is a parameter value measured by a sensor; when the parameter value is multiple, the layout point has multiple attribute values; since different attribute values may come from different sensors and the layout positions are different, the relationship diagram is the same or different for different attribute values;
preferably: the edges are weighted edges, when the difference of single characteristic values in the pipe network range where the two nodes are located is larger, the weight of the edges is larger, and otherwise, the weight of the edges is smaller; if the two nodes are in the pipe network range with the same characteristic value, the edge of the two nodes is the minimum value, such as 0; therefore, the actual pipe network layout condition can be substituted into the subsequent diagnosis process through the relational graph and the weighted edges thereof to form the relational graphs with local characteristics one by one, so that the obvious characteristics embodying the pipe network characteristics are participated in the subsequent diagnosis, and the clustering has boundary so as to obtain the clustering result conforming to the actual application condition for prediction; due to the corresponding relationship graphs of different attribute values, different attribute values can play different roles in the diagnosis process, so that the diagnosis is truly accurate from different dimensions;
s3, clustering the attribute values of the nodes based on the weight values of the edges in the relational graph to obtain a plurality of classes for each attribute value; clustering to obtain a communication value between nodes in any type, wherein the communication value is smaller than a preset value; the communication value between the nodes is the sum of the weights of the shortest path between the two nodes and the edges;
the actual spatial characteristics of the pipe network cannot be considered only by considering parameter values, so that common clustering modes such as k-means cannot be applied to a diagnosis method considering weighted edges, and the clustering error is large; in the invention, the core nodes are searched based on the layout point relational graph and the node distribution and combination are carried out through the nodes contained in the neighborhood of the core nodes, so that the time period can be accurately and quickly divided;
preferably: acquiring parameter values of the layout points as attribute values of the nodes through a sensor; because a plurality of sensors of different types can be arranged at the same layout point, a plurality of sensor parameters correspond to a plurality of different attribute values of the same layout point;
preferably: the preset value is twice of the neighborhood radius of the clustering center;
the clustering of the attribute values of the nodes based on the weight values of the edges in the relational graph to obtain a plurality of classes specifically comprises the following steps:
step SA 1: traversing nodes Ni in the relational graph;
step SA 2: searching Ni neighborhood nodes contained in the node Ni neighborhood range by taking the node Ni as a center; if the number of the Ni neighborhood nodes is more than or equal to the threshold number, setting the node Ni as an initial node, creating a class for the initial node, and adding all the nodes which are directly connected with the initial node in the neighborhood range of the initial node and have the weight of edges smaller than the radius r of the neighborhood into the newly created class; obtaining a plurality of initial clusters after traversing the node Ni; wherein: the neighborhood range of the node Ni takes the node Ni as a center, and the path length from the node Ni is smaller than the range within the neighborhood radius r; the path length is the sum of the weights of the edges contained in the path between any two nodes;
preferably: selecting a neighborhood radius according to the size of a pipe network coverage area targeted by diagnosis, considering that when the radius of the neighborhood is larger, the clustering quantity is small, a diagnosis model is insensitive, the calculation quantity is relatively small, and vice versa, wherein a balance is required; a relative balance between the two can be achieved by dynamic domain radius modification;
step SA 3: for each initial cluster, if a plurality of initial nodes exist in the same initial cluster, merging the plurality of initial clusters corresponding to the plurality of initial nodes; selecting one initial node from the multiple combined initial nodes as a cluster center of the combined initial cluster; the method of selection may be based on weight or attribute values;
for example: selecting the initial node closest to the average value of the initial node attributes as a selected clustering center;
step SA 4: performing cluster optimization on a plurality of initial clusters corresponding to the initial nodes; the method specifically comprises the following steps:
step SA 41: for each initial cluster, calculating the difference value between the cluster center attribute value of the initial cluster and the average attribute value of all nodes in the initial cluster;
step SA 42: carrying out optimization processing in sequence from the initial cluster with the largest difference value; for an initial cluster, sequentially selecting a node according to the sequence of the path length from the large to the small of the cluster center, and reselecting the initial cluster for the selected node according to the attribute value of the selected node;
reselecting the initial cluster for the selected node according to the attribute value of the selected node; the method specifically comprises the following steps: dividing the nodes into initial clusters with the minimum difference between the nodes and the attribute values; however, if only attribute values are considered, the nodes can easily break the weight edges representing the spatial characteristics in the clustering process; the weighting factor can therefore be further taken into account when making the reselection;
alternatively: reselecting the initial cluster for the selected node according to the attribute value of the selected node; the method specifically comprises the following steps:
when in use
Keeping the node in the first initial cluster, otherwise, dividing the node into the second initial cluster; wherein: n1 is a first initial cluster center, N2 is a second initial cluster center; the node is the selected node; path1 is the shortest Path length from the selected node to N1; path2 is the shortest Path length from the selected node to N2; a1 is the attribute value of N1, A2 is the attribute value of N2, AN is the attribute value of node;
step SA 43: recalculating the difference value between the cluster center attribute value and the initial cluster average attribute value of the current initial cluster, and returning to the step SA41 to reselect one initial cluster for optimization when the difference value meets the optimization target;
step SA 44: this step SA4 ends when all initial clusters meet the optimization objective;
by means of the clustering and clustering optimization mode, the initial mode of random seed sowing in the prior art is abandoned, large-range pipe network diagnosis becomes possible, and by means of the neighborhood range initial mode and the optimization mode based on the weight edges and the paths thereof, the diagnosis is carried out by integrating the attribute values while considering the actual physical conditions, so that a foundation is laid for accurate diagnosis;
the steps further include step S45: reselecting the initial clusters for all nodes which are not added into any initial clusters; if the number of the nodes which are not added into any initial cluster exceeds the percentage of the number of all the nodes and exceeds a preset percentage value, increasing the radius of the field for re-clustering or adding clusters to the nodes which are not added into any initial cluster;
step S4: for each attribute value, performing classification abnormity judgment on the gas network based on a clustering result; the method specifically comprises the following steps:
step S41: for each attribute value, analyzing the topological structure of the clustering result to generate a first diagnostic input; the topological position of the clustering center in the whole gas pipe network is clearly described through the step; for example: analyzing shortest path lengths between cluster centers and setting a first diagnostic input as a matrix of n x n, I1, where I1i，jThe shortest path length from the ith clustering center to the jth clustering center is obtained;
alternatively: setting a first diagnostic input as an n-ary vector, wherein I1iThe minimum value of the shortest path value from the ith clustering center to other clustering centers; some topology information may be lost at this time;
alternatively: setting a first diagnostic input as an n-ary vector, wherein I1i＝(xi,yi) The actual physical position of the ith clustering center in the tracheal net is taken as the position of the ith clustering center; for small-sized air pipe networks, or simplified air pipe network analysis, the input setting is feasible;
step S42: analyzing according to the node attribute value of the clustering result to generate a second diagnosis input; for example: a vector formed by the node attribute values of each cluster center node is used as a second diagnosis input;
step S43: performing a classification anomaly determination based on the first diagnostic input and the second diagnostic input; specifically, the method comprises the following steps: comparing the first diagnostic input and the second diagnostic input with historical diagnostic inputs respectively, and when the first diagnostic input and the second diagnostic input are changed, determining that classification abnormity occurs, otherwise, determining that no classification abnormity occurs;
preferably: the historical diagnosis input is historical first diagnosis input and historical second diagnosis input which are obtained according to historical data; wherein: the historical data is obtained by accumulating according to a plurality of detection results, and the accumulated data is used as historical data to be analyzed and processed to obtain historical first diagnostic input and historical second diagnostic input; or the historical diagnosis input is the previous-time diagnosis input and the previous-time second diagnosis input which are obtained according to the previous-time node and the attribute value of the previous-time node;
comparing the first diagnostic input with the historical diagnostic input specifically comprises: when the cluster number changes, the first diagnosis input is considered to change; when the number of the clustering centers is kept unchanged and the acceptable part of the clustering center nodes is changed, the first diagnosis input is not changed, otherwise, the first diagnosis input is changed; the acceptable portion here is changed such that the ratio of the number of nodes that are changed is less than the acceptable preset number; when the cluster center node is not changed, the second diagnosis input is not changed;
further: when the acceptable part of the nodes corresponding to the clustering centers is changed, but the nodes corresponding to the new clustering centers after the change and the nodes corresponding to the clustering centers before the change belong to the same cluster, the first diagnosis input is considered to be unchanged, otherwise, the first diagnosis input is considered to be changed;
comparing the second diagnostic input with the historical diagnostic input specifically comprises: calculating a distance between the second diagnostic input and the historical second diagnostic input, and when the distance is greater than a distance threshold, considering that the second diagnostic input has changed; for example: the distance is the Euclidean distance;
when the change occurs, it is considered that a classification abnormality occurs, specifically: when the first diagnosis input and the second diagnosis input are changed, the classification abnormity occurs, otherwise, the classification abnormity does not occur;
alternatively: the step S43 is: performing artificial intelligence classification anomaly determination based on the first diagnostic input and the second diagnostic input; the method comprises the following steps:
step S431: generating a third diagnostic input as a function of the first diagnostic input and the second diagnostic input; specifically, the method comprises the following steps: stitching the first diagnostic input and the second diagnostic input to generate a third diagnostic input;
alternatively, the first diagnostic input is functionally transformed through the second diagnostic input to obtain a third diagnostic input; i3 ═ f (I1, I2);
step S432: inputting a third diagnostic input to the neural network model to obtain a classification anomaly determination result;
before diagnosis is performed by adopting the neural network model, training the neural network model according to historical first diagnosis input and second diagnosis input; the intelligent method of the invention integrates the actual pipe network condition, integrates the real-time detection result, increases the completeness and diversity of input, and is beneficial to the abnormity diagnosis of the complex gas pipe network;
step S5: performing abnormality diagnosis based on the classified abnormality determination result; specifically, the method comprises the following steps: performing abnormity diagnosis based on the classification abnormity judgment result corresponding to each type of attribute value; for example: through a voting judgment mode, when the majority classification abnormity judgment result is abnormal, judging that the complex trachea network is abnormal;
preferably: when all the classification abnormity determination results are abnormal, determining that the complex tracheal network is abnormal;
the various illustrative logical blocks, modules, and circuits described may be implemented or performed with a general purpose processor, a Digital Signal Processor (DSP), an ASIC, a field programmable gate array signal (FPGA) or other Programmable Logic Device (PLD), discrete gate or transistor logic, discrete hardware components, or any combination thereof designed to perform the functions described herein. A general purpose processor may be a microprocessor, but in the alternative, the processor may be any commercially available processor, controller, microcontroller or state machine. A processor may also be implemented as a combination of computing devices, e.g., a combination of a DSP and a microprocessor, a plurality of microprocessors, one or more microprocessors in conjunction with a DSP core, or any other such configuration. The steps of a method or algorithm described in connection with the present disclosure may be embodied directly in hardware, in a software module executed by a processor, or in a combination of the two. The software modules may reside in any form of tangible storage medium. Some examples of storage media that may be used include Random Access Memory (RAM), Read Only Memory (ROM), flash memory, EPROM memory, EEPROM memory, registers, hard disk, removable disk, CD-ROM, and the like. A storage medium may be coupled to the processor such that the processor can read information from, and write information to, the storage medium. In the alternative, the storage medium may be integral to the processor. A software module may be a single instruction, or many instructions, and may be distributed over several different code segments, among different programs, and across multiple storage media.
The functions described may be implemented in hardware, software, firmware, or any combination thereof. If implemented in software, the functions may be stored as one or more instructions on a tangible computer-readable medium. The computer readable medium includes a computer readable storage medium. Computer readable storage media can be any available storage media that can be accessed by a computer. By way of example, and not limitation, such computer-readable media can comprise RAM, ROM, EEPROM, CD-ROM or other optical disk storage, magnetic disk storage or other magnetic storage devices, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and that can be accessed by a computer. Additionally, propagated signals are not included within the scope of computer-readable storage media. Computer-readable media also includes communication media including any medium that facilitates transfer of a computer program from one place to another. The connection may be, for example, a communication medium. For example, if the software is transmitted from a web site, server, or other remote source using a coaxial cable, fiber optic cable, twisted pair, Digital Subscriber Line (DSL), or wireless technologies such as infrared, radio, and microwave, then the coaxial cable, fiber optic cable, twisted pair, DSL, or wireless technologies such as infrared, radio, and microwave are included in the definition of communication medium. Combinations of the above should also be included within the scope of computer-readable media. Alternatively or in addition, the functions described herein may be performed, at least in part, by one or more hardware logic components. For example, illustrative types of hardware logic components that may be used include Field Programmable Gate Arrays (FPGAs), program specific integrated circuits (ASICs), program specific standard products (ASSPs), system on a chip (SOCs), Complex Programmable Logic Devices (CPLDs), and so forth.
Accordingly, a computer program product may perform the operations presented herein. For example, such a computer program product may be a computer-readable tangible medium having instructions stored (and/or encoded) thereon that are executable by one or more processors to perform the operations described herein. The computer program product may include packaged material.
Software or instructions may also be transmitted over a transmission medium. For example, the software may be transmitted from a website, server, or other remote source using a transmission medium such as coaxial cable, fiber optic cable, twisted pair, Digital Subscriber Line (DSL), or wireless technologies such as infrared, radio, or microwave.
Further, modules and/or other suitable means for carrying out the methods and techniques described herein may be downloaded and/or otherwise obtained by a user terminal and/or base station as appropriate. For example, such a device may be coupled to a server to facilitate the transfer of means for performing the methods described herein. Alternatively, the various methods described herein can be provided via storage means (e.g., RAM, ROM, a physical storage medium such as a CD or floppy disk) so that the user terminal and/or base station can obtain the various methods when coupled to or providing storage means to the device. Further, any other suitable technique for providing the methods and techniques described herein to a device may be utilized.
The above description is only a preferred embodiment of the present invention, and all equivalent changes or modifications of the structure, characteristics and principles described in the present invention are included in the scope of the present invention.
Claims (10)
1. A method for diagnosing the abnormality of an urban complex tracheal network is characterized by comprising the following steps:
step S1: for each sensor type, differentially selecting layout points on the tracheal net and laying sensors;
step S2: connecting the layout points based on the topological relation of the pipe network to form a layout point relation graph;
step S3: clustering attribute values of the nodes based on the weight values of the edges in the relational graph to obtain a plurality of classes;
step S4: performing classification abnormity judgment on the gas network based on the clustering result;
step S5: and performing abnormality diagnosis based on the classified abnormality determination result.
2. The method for diagnosing the abnormality of the urban complex gas pipe network according to claim 1, wherein the step S1 specifically comprises: the distribution points are uniformly arranged in the tracheal tube segment in the non-special area, and the distribution points are selected in the special area so that the number of the distribution points is not less than the minimum distribution value.
3. The method for diagnosing the abnormality of the urban complex gas pipe network according to claim 2, wherein the uniform setting can be selecting a distribution point in a given area or setting the pipe network in a preset area to a preset length.
4. The method according to claim 3, wherein the minimum distribution value is a preset value.
5. The method for diagnosing the abnormality of the urban complex gas pipe network according to claim 4, wherein when the minimum distribution value cannot be met, the special area is calibrated according to a single data characteristic.
6. The method for diagnosing the abnormality of the urban complex gas pipe network according to claim 5, wherein a layout point is selected at the boundary of the special area, and the sensors are arranged at the layout point.
7. The method for diagnosing the abnormality of the urban complex gas pipe network according to claim 6, wherein the preset length is 50M.
8. An abnormality diagnosis device for an urban complex tracheal network, comprising:
a storage unit configured to store an application program; and
a processing unit electrically coupled to an input unit and the storage unit, the processing unit configured to perform the method of claims 1-7.
9. An abnormality diagnosis system for a complex urban tracheal network, comprising: a server and a client;
the client is used for sending an abnormity diagnosis request of the urban complex trachea network to the server;
the server is configured to perform the method of claims 1-7 and send the request result to the client.
10. An urban complex tracheal network anomaly diagnosis storage medium, wherein the storage medium is configured to store instructions for performing the method of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110547193.2A CN113357545B (en) | 2021-05-19 | 2021-05-19 | Method and system for diagnosing abnormity of urban complex gas pipe network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110547193.2A CN113357545B (en) | 2021-05-19 | 2021-05-19 | Method and system for diagnosing abnormity of urban complex gas pipe network |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113357545A true CN113357545A (en) | 2021-09-07 |
| CN113357545B CN113357545B (en) | 2023-04-18 |
Family
ID=77526931
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110547193.2A Active CN113357545B (en) | 2021-05-19 | 2021-05-19 | Method and system for diagnosing abnormity of urban complex gas pipe network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113357545B (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102235575A (en) * | 2010-04-29 | 2011-11-09 | 国际商业机器公司 | Data processing method and system for checking pipeline leakage |
| US20130262068A1 (en) * | 2012-03-28 | 2013-10-03 | International Business Machines Corporation | Sensor placement for leakage location in liquid distribution networks |
| CN103491651A (en) * | 2013-09-25 | 2014-01-01 | 河海大学 | Abnormal/fault positioning detection method based on binomial tree model |
| CN107420743A (en) * | 2017-06-09 | 2017-12-01 | 中国计量大学 | A kind of intelligent city's combustion gas PE pipe networks TT＆C system and investigating method |
| CN111022932A (en) * | 2019-12-12 | 2020-04-17 | 上海邦芯物联网科技有限公司 | Sensor point distribution system and method for water supply pipe network |
| CN111076096A (en) * | 2019-12-31 | 2020-04-28 | 北京讯腾智慧科技股份有限公司 | Gas pipe network leakage identification method and device |
| CN111277469A (en) * | 2020-02-19 | 2020-06-12 | 杜义平 | Network diagnosis processing method and device, network system and server |
-
2021
- 2021-05-19 CN CN202110547193.2A patent/CN113357545B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102235575A (en) * | 2010-04-29 | 2011-11-09 | 国际商业机器公司 | Data processing method and system for checking pipeline leakage |
| US20130262068A1 (en) * | 2012-03-28 | 2013-10-03 | International Business Machines Corporation | Sensor placement for leakage location in liquid distribution networks |
| CN103491651A (en) * | 2013-09-25 | 2014-01-01 | 河海大学 | Abnormal/fault positioning detection method based on binomial tree model |
| CN107420743A (en) * | 2017-06-09 | 2017-12-01 | 中国计量大学 | A kind of intelligent city's combustion gas PE pipe networks TT＆C system and investigating method |
| CN111022932A (en) * | 2019-12-12 | 2020-04-17 | 上海邦芯物联网科技有限公司 | Sensor point distribution system and method for water supply pipe network |
| CN111076096A (en) * | 2019-12-31 | 2020-04-28 | 北京讯腾智慧科技股份有限公司 | Gas pipe network leakage identification method and device |
| CN111277469A (en) * | 2020-02-19 | 2020-06-12 | 杜义平 | Network diagnosis processing method and device, network system and server |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113357545B (en) | 2023-04-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109555979B (en) | Water supply pipe network leakage monitoring method | |
| Liu et al. | A leak detection method for oil pipeline based on Markov feature and two-stage decision scheme | |
| Burdakis et al. | Detecting outliers in sensor networks using the geometric approach | |
| CN108306756A (en) | One kind being based on electric power data network holography assessment system and its Fault Locating Method | |
| CN107273273A (en) | A kind of distributed type assemblies hardware fault method for early warning and system | |
| CN108491931B (en) | Method for improving nondestructive testing precision based on machine learning | |
| CN105512011B (en) | A kind of electronics testability modeling appraisal procedure | |
| CN111950627A (en) | Multi-source information fusion method and application thereof | |
| Ma et al. | A novel broad learning system based leakage detection and universal localization method for pipeline networks | |
| CN110929359A (en) | Pipe network siltation risk prediction modeling method based on PNN neural network and SWMM technology | |
| CN115654381A (en) | Water supply pipeline leakage detection method based on graph neural network | |
| Guo et al. | Monitoring and simulation of dynamic spatiotemporal land use/cover changes | |
| WO2020153903A1 (en) | Method and system for monitoring a gas distribution network operating at low pressure | |
| CN112434887B (en) | Water supply network risk prediction method combining network kernel density estimation and SVM | |
| CN110011847A (en) | A kind of data source method for evaluating quality under sensing cloud environment | |
| CN113357545B (en) | Method and system for diagnosing abnormity of urban complex gas pipe network | |
| Maervoet et al. | Outlier detection in relational data: A case study in geographical information systems | |
| CN110222098A (en) | Electric power high amount of traffic abnormality detection based on flow data clustering algorithm | |
| CN113094853A (en) | Optimized layout method and system for gas pipe network leakage positioning | |
| CN109341650B (en) | Unmanned aerial vehicle elevation error double-threshold correction method based on minimum detection cost | |
| CN113326596A (en) | Method and system for setting detection points of complex gas pipe network structure | |
| CN115951123A (en) | Electric energy metering method and system based on wireless communication | |
| CN113744888B (en) | Regional epidemic trend prediction and early warning method and system | |
| Wang et al. | Hierarchical stroke mesh: A new progressive matching method for detecting multi-scale road network changes using OpenStreetMap | |
| CN112097125B (en) | Water supply pipe network pipe burst detection and positioning method based on self-adaptive checking |
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 |