CN113341813A - Urban gas medium-low pressure pipe network detection method and system - Google Patents
Urban gas medium-low pressure pipe network detection method and system Download PDFInfo
- Publication number
- CN113341813A CN113341813A CN202110654129.4A CN202110654129A CN113341813A CN 113341813 A CN113341813 A CN 113341813A CN 202110654129 A CN202110654129 A CN 202110654129A CN 113341813 A CN113341813 A CN 113341813A
- Authority
- CN
- China
- Prior art keywords
- layer
- pipe network
- low pressure
- data
- pressure pipe
- 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
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B19/00—Programme-control systems
- G05B19/02—Programme-control systems electric
- G05B19/04—Programme control other than numerical control, i.e. in sequence controllers or logic controllers
- G05B19/042—Programme control other than numerical control, i.e. in sequence controllers or logic controllers using digital processors
- G05B19/0428—Safety, monitoring
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B2219/00—Program-control systems
- G05B2219/20—Pc systems
- G05B2219/24—Pc safety
- G05B2219/24024—Safety, surveillance
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Automation & Control Theory (AREA)
- Pipeline Systems (AREA)
Abstract
The invention relates to a detection system for a medium-low pressure pipe network in urban gas, which comprises an equipment layer, an edge layer and a cloud computing layer, wherein the equipment layer, the edge layer and the cloud computing layer are connected through a communication network; the device layer comprises a plurality of intelligent instruments and control equipment, and the control equipment is used for reading real-time detection data stored in the edge layer storage end by the intelligent instruments and judging whether to further judge the abnormal state of the pipe network according to the excitation threshold value of the real-time physical parameter prestored in the control equipment.
Description
Technical Field
The invention relates to the field of energy delivery, in particular to a method and a system for detecting a medium-low pressure pipe network in urban gas.
Background
With the development of intelligent technology, a large number of intelligent instruments are applied to daily monitoring of urban gas pipe networks. In the prior art, an intelligent detection instrument of a gas pipe network with large-scale and complex data information is generally calculated and monitored by an edge calculation system. The edge computing is a system which is close to one side of a data measurement source and provides a nearest server side nearby by adopting an open platform with the core capabilities of network, computing, storage and application. Although computing and network resources have been greatly saved compared to earlier cloud computing systems, the edge computing system currently applied to city gas pipeline network monitoring has the following problems: 1) the degree of the device end intervening in the whole calculation or monitoring management program is low, the device layer is mainly used for detecting data, most of calculation is carried out in a cloud calculation layer or an edge layer, and the network load needs to be further reduced; 2) the judgment of the faults of the gas pipe network is usually directly carried out through large-scale data calculation, a flexible and economical judgment mode is lacked, and the utilization efficiency of computing resources needs to be further improved; 3) the accuracy of the calculation result needs to be further improved.
Therefore, the method and the system for detecting the medium-low pressure pipe network in the urban gas, which improve the participation degree of the equipment end, have a flexible and economical judgment mode and accurate calculation results, are needed to be provided.
Disclosure of Invention
The technical problem to be solved by the invention is the following defects in the prior art: 1) the degree of the device end intervening in the whole calculation or monitoring management program is low, the device layer is mainly used for detecting data, most of calculation is carried out in a cloud calculation layer or an edge layer, and the network load needs to be further reduced; 2) the judgment of the faults of the gas pipe network is usually directly carried out through large-scale data calculation, a flexible and economical judgment mode is lacked, and the utilization efficiency of computing resources needs to be further improved; 3) the accuracy of the calculation result needs to be further improved.
The technical scheme adopted by the invention for solving the technical problems is as follows:
a system for detecting a medium-low pressure pipe network in urban gas comprises an equipment layer, an edge layer and a cloud computing layer, wherein the equipment layer, the edge layer and the cloud computing layer are connected through a communication network; the device layer comprises a plurality of intelligent instruments and control equipment, and the control equipment is used for reading real-time detection data stored in the edge layer storage end by the intelligent instruments, monitoring whether various parameters in the real-time data exceed respective class excitation thresholds, and judging whether further judgment is carried out on abnormal pipe network states.
Further, this intelligent instrument is installed at the branch pipeline end of low pressure pipe network in the city gas.
Further, the control device is provided in such a manner that one control device is provided for a plurality of end pipes within a certain range.
Further, the control device is provided in such a manner that a plurality of control devices are provided at a plurality of end pipes within a certain range.
Furthermore, the intelligent instrument is one or more of a pressure sensing intelligent instrument, a temperature sensing intelligent instrument and a flow sensing intelligent instrument.
Further, the intelligent instrument can also be a humidity sensing intelligent instrument.
A method for detecting a medium-low pressure pipe network in urban gas is based on the system for detecting the medium-low pressure pipe network in the urban gas.
Further, the method comprises: and step S1, uploading the real-time detection data of the n intelligent instruments of the equipment layer installed on the plurality of tail end pipelines of the medium and low pressure gas pipeline network to a storage end of the edge layer for storage.
Further, the method comprises: and the control equipment in the equipment layer reads the real-time data stored in the storage end and monitors whether various parameters in the real-time data exceed the excitation threshold values of the various types of the parameters.
Further, the method comprises: the control equipment sends a request instruction for further judging the pipeline abnormity to the cloud computing layer, and the cloud computing layer determines a classification model according to the instruction.
The application provides a low pressure pipe network detection method and system in city gas for this application has following beneficial effect:
1) by setting the control equipment of the equipment layer, most of work of reading real-time data is left at the equipment end close to the edge layer, and network resources are saved.
2) The abnormal condition of the pipeline is judged through three levels of primary judgment of control equipment, automatic classifier classification of a cloud computing layer and final digital model calculation, so that the obvious non-fault condition can be eliminated at the earliest by using the minimum network resources, and the network fault which can be judged only by performing massive data calculation is further screened out by using a classifier model and limited data of the cloud computing layer, the system burden caused by large-scale calculation is further avoided, and finally, the judgment accuracy can be improved by pertinently setting a calculation model aiming at different possible fault types.
3) In the classifier model classification process of the cloud computing layer, the thought that the more the abnormal data distance is close to the time exceeding the excitation threshold data acquisition time, the more the possible abnormal risk of the pipeline is caused is combined, the time parameter is taken into consideration after the classifier model classification, misjudgment caused by the fact that the early data of the classifier are too sensitive and omission of dangerous conditions caused by the fact that the weight of the recent data on the pipeline influence is not considered sufficiently are avoided, and the accuracy of detection is improved.
Drawings
Fig. 1 is a schematic structural diagram of a system for detecting a medium-low pressure pipe network in urban gas according to the present application.
Detailed Description
The present invention will now be described in more detail with reference to the accompanying drawings, in which preferred embodiments of the invention are shown, it being understood that one skilled in the art may modify the invention herein described while still achieving the beneficial results of the present invention. Accordingly, the following description should be construed as broadly as possible to those skilled in the art and not as limiting the invention.
In the interest of clarity, not all features of an actual implementation are described. In the following description, well-known functions or constructions are not described in detail since they would obscure the invention in unnecessary detail. It will of course be appreciated that in the development of any such actual embodiment, numerous implementation-specific details must be set forth in order to achieve the developer's specific goals.
In order to make the objects and features of the present invention more comprehensible, embodiments of the present invention are described in detail below with reference to the accompanying drawings. It is to be noted that the drawings are in a very simplified form and are intended to use non-precision ratios for the purpose of facilitating and clearly facilitating the description of the embodiments of the invention.
The application firstly provides a detection system for a medium-low pressure pipe network in urban gas, and the structural schematic diagram of the system is shown in figure 1. Referring to fig. 1, the urban gas medium and low pressure pipe network detection system provided by the application comprises an equipment layer, an edge layer and a cloud computing layer, wherein the equipment layer, the edge layer and the cloud computing layer are connected through a communication network.
The device layer comprises a detection end and a control device. The detection end comprises n sensors, the n sensors are distributed on the tail end pipelines of the low-pressure pipe networks in the urban gas, for example: the end of an in-home conduit or a conduit of a unit building. The n sensors may be one or more types of intelligent instruments having a sensing function, and the one or more types of intelligent instruments may be one or more types of pressure sensing intelligent instruments, temperature sensing intelligent instruments, flow sensing intelligent instruments and humidity sensing intelligent instruments. The intelligent instrument with the sensing function is used for detecting real-time physical parameter data of a tail end pipeline and uploading the data to a storage end in an edge layer through a network.
The device layer further comprises a control device, the control device is used for reading real-time detection data stored in the edge layer storage end by the intelligent instrument, and judging whether further judgment of whether the pipe network state is preliminary abnormal or not in the cloud computing layer is needed or not by comparing an excitation threshold value of a real-time physical parameter prestored in the control device with a corresponding real-time detection data value.
The control device may be provided in such a manner that a plurality of end pipes within a certain range are provided with one control device, for example: if the end pipes are not home pipes, a control device may be configured within one or more building areas to control the detection of physical parameters of all end pipes within the area. Although fig. 1 shows only one control device, a plurality of control devices may be configured according to the number and the position distribution of the end pipes, so that a plurality of end pipes in a range are divided into a plurality of sub-areas for respective control detection. The control equipment can be computer equipment such as an industrial upper computer.
The control device is further configured to: when the judgment result of whether the network management state is preliminary abnormal or not is carried out on the cloud computing layer, and the final abnormal condition is determined by carrying out physical parameter data computing of the network management state, a control command sent by the cloud computing layer is received, wherein the control command comprises information such as a data range required by the physical parameter data computing, a computing task and a computing model related to the computing task, and after receiving the control command, the control device decomposes the computing task according to the performability of a program, and sends the decomposed computing task to a plurality of computing nodes respectively according to the computing task decomposition result for unloading computing. And finally feeding the respective calculation results back to the cloud calculation layer by the plurality of calculation nodes, and after the cloud calculation layer fuses the final calculation results, further judging whether the management network state is abnormal or not based on the physical parameter data calculation result of the management network state.
For example: when the cloud computing layer judges that the current pipe network has primary abnormity and the type of the primary abnormity is the abnormal blockage risk, physical parameter data calculation of the pipe network state in the abnormal blockage mode is needed to determine the final abnormal condition, and the cloud computing layer comprises a data range required by calculation in the abnormal blockage mode, namely pressure, temperature and flow parameters of a corresponding tail end pipeline within 2 hours, and a calculation task, wherein the data range comprises: 1) fitting a fitting function formed by real-time pressure and time of the tail end pipeline; 2) correcting the fitting function according to the temperature compensation and the flow-vortex parameter relation; 3) and performing Fourier transform (FFT) on the corrected fitting function to obtain a frequency domain function, and extracting a high-intensity frequency signal to judge whether the pipeline has a blockage risk. After receiving the computing tasks, the control device decomposes the three computing steps into a plurality of sub-computing tasks according to the performability of the program, and sends the sub-computing tasks of each step to a plurality of computing nodes of the edge layer respectively in a computing instruction mode to carry out unloading computing.
In the above, only the case of the preliminary blocking abnormality is listed, and for the case of leakage and other abnormalities, the skilled person can design the related calculation steps according to the technical knowledge grasped by the skilled person, and the technical arrangement is not the contribution point of the invention of the present application, and therefore, the detailed description is omitted here.
The edge layer comprises a storage end and a calculation end. The storage end is used for storing the detection data uploaded by the n intelligent meters in real time. The computing end comprises m computing nodes, and the computing nodes are used for computing the unloaded sub-computing tasks according to the computing instructions of the control equipment.
The cloud computing layer is remotely connected to the edge layer, the cloud computing layer can read data of the edge layer, and the cloud computing layer trains and stores classifier models of multiple categories in advance, wherein the classifier can be an SVM classifier. And respectively designing and training different classifier models according to the data types of different dimension combinations. For example: different classifier models are corresponding to different data types such as pressure-temperature data, flow-pressure-time data, flow-time data and the like. The classifier is designed and trained by firstly establishing known detection parameter samples of given types of data including historical non-fault data, historical blocking state data, historical leakage state data and historical other abnormal state data, then adjusting a criterion function, and finally solving an extreme value solution of the criterion function by a mathematical method of solving an optimal solution so as to obtain a weight vector and a threshold weight. The classifier can automatically classify a plurality of multi-dimensional physical parameter values (such as pressure-temperature-time three-dimensional or pressure-flow-temperature-time multi-dimensional) continuously collected within a period of time into historical non-fault data, historical blockage state data, historical leakage state data and historical other abnormal state data. And judging whether the preliminary abnormity exists and the preliminary abnormity type according to the classified statistical result.
The cloud computing layer is also used for fusing the computing results made by the plurality of computing nodes of the edge layer and further judging whether the state of the medium-low pressure pipe network is finally abnormal or not according to the fused results. For example, for the initial blockage abnormal condition, the plurality of computing nodes finally feed back the respective computing results of step 3) to the cloud computing layer, the cloud computing layer fuses the final computing results to obtain a high-strength frequency signal, and further, the high-strength frequency signal is compared with a threshold value to determine whether the final blockage abnormal condition exists in the pipe network state.
According to the urban gas medium-low pressure pipe network detection system, the application also provides an urban medium-low pressure pipe network detection method, and the method comprises the following steps:
and step S1, uploading the real-time detection data of the n intelligent instruments of the equipment layer installed on the plurality of tail end pipelines of the medium and low pressure gas pipeline network to a storage end of the edge layer for storage.
Specifically, the real-time data can be classified and stored by classifying corresponding terminal pipelines, parameter types and time periods, so that access and calling in the subsequent calculation process are facilitated.
Step S2, the control device in the device layer reads the real-time data stored in the storage end, and monitors whether various parameters in the real-time data exceed their respective excitation thresholds.
Specifically, after real-time detection data of the intelligent instrument is uploaded to a storage end of the edge layer, the control device simultaneously reads the stored data in real time, and judges whether the real-time data exceeds an excitation threshold value of the type of the real-time data according to the type of the real-time data and a numerical value of the real-time data. And comparing the excitation threshold value of the real-time physical parameter prestored in the control equipment with the corresponding real-time detection data value to judge whether further judgment on whether the pipe network state is preliminarily abnormal or not needs to be carried out on the cloud computing layer.
The excitation threshold may be a fixed value calculated empirically by one skilled in the art, or a derivative of the average of accumulated real-time data. For example, the excitation threshold for the pressure category of the pipeline pressure may be 0.6Mpa at the upper end and 0.005Mpa at the lower end, or ± 20% of the average of the pressure data accumulated over 24 hours. As the excitation threshold for exciting the further determination, in order to avoid missing the abnormal state, the range of the excitation threshold is generally set to be relatively wide, that is, as many cases as possible are included.
If the real-time data exceeds the threshold of arousal for the category to which it belongs, step S3 is performed, and if the real-time data does not exceed the threshold of arousal for the category to which it belongs, step S2 is continuously performed.
Step S3, the control device sends a request instruction for further determining whether the network state is initially abnormal or not on the cloud computing layer, and the cloud computing layer further determines the initial abnormality according to the request instruction.
Specifically, the request instruction includes a data type exceeding the trigger threshold, a data value, and a corresponding time. The cloud computing layer calls pre-stored data of different types according to the request instruction, and determines the parameter type and the data detection time period which need to be called from the storage end and the corresponding classifier model stored in the cloud computing layer according to the type of the data. For example: the control device judges that the pressure parameter at the time t1 exceeds the excitation threshold, and the cloud computing end determines real-time temperature, pressure and flow data 1 hour before the time t1 is called to the memory according to a pre-stored classification model, and determines a classifier model for classifying the temperature-pressure-flow-time data.
Step S4, the cloud computing layer generates and sends a data acquisition request to the storage end according to the data call requirement, and after receiving the data acquisition request, the storage end sends corresponding data to the cloud computing layer according to the requirement of the cloud computing layer and stores the data in the cache portion of the cloud computing layer.
Specifically, the data acquisition request includes a parameter type and a data detection time period called from the storage terminal. And after receiving the information, the storage terminal sends the real-time data of the specific type in the specific detection time period to the cloud computing layer for classified computing. And after receiving the required data, the cloud computing layer stores the data in a cache part of the cloud computing layer.
In step S5, the cloud computing layer determines whether the pipeline is in a preliminary abnormal state based on the received data and the corresponding classifier model, and determines the type of the preliminary abnormal state. If the pipe state is judged to be preliminary abnormal, it is necessary to determine the final abnormal situation through the physical parameter data calculation of the pipe network state in the mode of the specific preliminary abnormal, and send a control command to the control device for driving further calculation, and if the pipe state is judged to be preliminary normal, it returns to step S1.
Specifically, the cloud computing layer classifies all the multidimensional data points in the multidimensional space based on the received data through classifier models of corresponding types, and the classifier models can respectively design and train different classifier models for SVM classifiers according to data types of different dimensional combinations. For example: different classifier models are corresponding to different data types such as pressure-temperature data, flow-pressure-time data, flow-time data and the like. The classifier is designed and trained by firstly establishing known detection parameter samples of given types of data including historical non-fault data, historical blocking state data, historical leakage state data and historical other abnormal state data, then adjusting a criterion function, and finally solving an extreme value solution of the criterion function by a mathematical method of solving an optimal solution so as to obtain a weight vector and a threshold weight. The classifier can automatically classify a plurality of multi-dimensional physical parameter values (such as pressure-temperature-time three-dimensional or pressure-flow-temperature-time multi-dimensional) continuously collected within a period of time into historical non-fault data, historical blockage state data, historical leakage state data and historical other abnormal state data. And judging whether the preliminary abnormity exists and the preliminary abnormity type according to the classified statistical result.
Through the classifier models of different types, data called by the cloud computing layer are divided into four types of historical non-fault data, historical blocking state data, historical leakage state data and historical other abnormal state data. Setting the assignment x of the fault data points classified into historical jam state data, historical leakage state data and historical other abnormal state data as-1, setting the assignment x classified into non-fault data points as 1, if sigma (t1-Ti) Xi is greater than 0, judging the pipeline state to be preliminary normal without further calculation and determination, and if sigma (t1-Ti) Xi is less than or equal to 0, judging the pipeline state to be preliminary abnormal and requiring further calculation and determination. Wherein t1 represents the acquisition time of the data point exceeding the excitation threshold, Ti represents the acquisition time of the ith data point, i represents any one of all data acquired by the cloud computing layer according to the demand request, and Xi represents the assignment of the ith data point.
Through categorizing above-mentioned data to combine unusual data distance to surpass arousing that threshold value data acquisition time is closer, the thought that possible pipeline anomaly's that causes risk is big more, this application introduces the consideration of time parameter after classifier model classification, has avoided the early data of classifier to be too sensitive the misjudgment that causes and to near data to the omission of the dangerous condition that the weight consideration of pipeline influence is not enough to cause, the accuracy of the detection of improvement.
If further calculations with the physical parameter data of the state of the pipe network in the mode of the specific preliminary anomaly are required, a control command is sent to the control device for driving the further calculations, and if no further calculations are required, the procedure returns to step S1.
The control command includes information such as a data range required for calculation, a calculation task, and a calculation model related to the calculation task. The information of the computing task and the computing model involved in the computing task is different according to different types of possible faults. Specifically, the possible abnormal type is determined according to the proportion of historical jam state data, historical leakage state data and historical other abnormal state data in the data classification process, for example: and selecting a calculation model and a task aiming at the jam condition when the data is further calculated according to the maximum occupation ratio of the historical jam state data in the data classification process.
And S6, the control equipment decomposes the computing task according to the control command sent by the cloud computing layer and carries out unloading computing on the computing nodes of the edge layer.
Specifically, after receiving the control command, the control device decomposes the computing tasks according to the performability of the program, and sends the decomposed computing tasks to a plurality of computing nodes respectively according to the decomposition result of the computing tasks to perform unloading computation.
For example: when the cloud computing layer judges that the current pipe network has primary abnormity and the type of the primary abnormity is the abnormal blockage risk, physical parameter data calculation of the pipe network state in the abnormal blockage mode is needed to determine the final abnormal condition, and the cloud computing layer comprises a data range required by calculation in the abnormal blockage mode, namely pressure, temperature and flow parameters of a corresponding tail end pipeline within 2 hours, and a calculation task, wherein the data range comprises: 1) fitting a fitting function formed by real-time pressure and time of the tail end pipeline; 2) correcting the fitting function according to the temperature compensation and the flow-vortex parameter relation; 3) and performing Fourier transform (FFT) on the corrected fitting function to obtain a frequency domain function, and extracting a high-intensity frequency signal to judge whether the pipeline has a blockage risk. After receiving the computing tasks, the control device decomposes the three computing steps into a plurality of sub-computing tasks according to the performability of the program, and sends the sub-computing tasks of each step to a plurality of computing nodes of the edge layer respectively in a computing instruction mode to carry out unloading computing.
And S7, feeding the final calculation results of the plurality of calculation nodes back to the cloud calculation layer, fusing the calculation results made by the plurality of calculation nodes of the edge layer by the cloud calculation layer, and further judging whether the state of the medium-voltage and low-voltage pipe network is finally abnormal according to the fused result.
Specifically, for example, for the preliminary abnormal blocking situation, the plurality of computing nodes finally feed back the respective computing results of step 3) to the cloud computing layer, the cloud computing layer fuses the final computing results to obtain a high-strength frequency signal, and further, the high-strength frequency signal is compared with a threshold value to determine whether the final abnormal blocking exists in the pipe network state.
The application provides a low pressure pipe network detection method and system in city gas for this application has following beneficial effect:
1) by setting the control equipment of the equipment layer, most of work of reading real-time data is left at the equipment end close to the edge layer, and network resources are saved.
2) The abnormal condition of the pipeline is judged through three levels of primary judgment of control equipment, automatic classifier classification of a cloud computing layer and final digital model calculation, so that the obvious non-fault condition can be eliminated at the earliest by using the minimum network resources, and the network fault which can be judged only by performing massive data calculation is further screened out by using a classifier model and limited data of the cloud computing layer, the system burden caused by large-scale calculation is further avoided, and finally, the judgment accuracy can be improved by pertinently setting a calculation model aiming at different possible fault types.
3) In the classifier model classification process of the cloud computing layer, the thought that the more the abnormal data distance is close to the time exceeding the excitation threshold data acquisition time, the more the possible abnormal risk of the pipeline is caused is combined, the time parameter is taken into consideration after the classifier model classification, misjudgment caused by the fact that the early data of the classifier are too sensitive and omission of dangerous conditions caused by the fact that the weight of the recent data on the pipeline influence is not considered sufficiently are avoided, and the accuracy of detection is improved.
The foregoing illustrates and describes the principles, general features, and advantages of the present invention. It will be understood by those skilled in the art that the present invention is not limited to the embodiments described above, which are described in the specification and illustrated only to illustrate the principle of the present invention, but that various changes and modifications may be made therein without departing from the spirit and scope of the present invention, which fall within the scope of the invention as claimed. The scope of the invention is defined by the appended claims and equivalents thereof.
Claims (10)
1. The utility model provides a low pressure pipe network detecting system in city gas which characterized in that: the system comprises an equipment layer, an edge layer and a cloud computing layer, wherein the equipment layer, the edge layer and the cloud computing layer are connected through a communication network; the device layer comprises a plurality of intelligent instruments and control equipment, and the control equipment is used for reading real-time detection data stored in the edge layer storage end by the intelligent instruments, monitoring whether various parameters in the real-time data exceed respective class excitation thresholds, and judging whether further judgment is carried out on abnormal pipe network states.
2. The urban gas medium-low pressure pipe network detection system according to claim 1, characterized in that: the intelligent instrument is installed at the tail end of a branch pipeline of a low-pressure pipeline network in urban gas.
3. The urban gas medium-low pressure pipe network detection system according to claim 1, characterized in that: the control device is provided in such a manner that a plurality of end pipes within a certain range are provided with one control device.
4. The urban gas medium-low pressure pipe network detection system according to claim 1, characterized in that: the control device is provided in such a manner that a plurality of control devices are provided to a plurality of end pipes within a certain range.
5. The urban gas medium-low pressure pipe network detection system according to claim 2, characterized in that: the intelligent instrument is one or more of a pressure sensing intelligent instrument, a temperature sensing intelligent instrument and a flow sensing intelligent instrument.
6. The urban gas medium-low pressure pipe network detection system according to claim 5, characterized in that: the smart meter may also be a humidity sensing smart meter.
7. A method for detecting a medium-low pressure pipe network in urban gas is characterized by comprising the following steps: the method is based on the urban gas medium and low pressure pipe network detection system of one of claims 1 to 6.
8. The urban gas medium-low pressure pipe network detection method according to claim 7, characterized in that: the method comprises the following steps: and step S1, uploading the real-time detection data of the n intelligent instruments of the equipment layer installed on the plurality of tail end pipelines of the medium and low pressure gas pipeline network to a storage end of the edge layer for storage.
9. The urban gas medium-low pressure pipe network detection method according to claim 8, characterized in that: the method comprises the following steps: and the control equipment in the equipment layer reads the real-time data stored in the storage end and monitors whether various parameters in the real-time data exceed the excitation threshold values of the various types of the parameters.
10. The urban gas medium-low pressure pipe network detection method according to claim 9, characterized in that: the method comprises the following steps: the control equipment sends a request instruction for further judging the pipeline abnormity to the cloud computing layer, and the cloud computing layer determines a classification model according to the instruction.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110654129.4A CN113341813B (en) | 2021-06-11 | 2021-06-11 | Urban gas medium-low pressure pipe network detection method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110654129.4A CN113341813B (en) | 2021-06-11 | 2021-06-11 | Urban gas medium-low pressure pipe network detection method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113341813A true CN113341813A (en) | 2021-09-03 |
| CN113341813B CN113341813B (en) | 2022-11-01 |
Family
ID=77476872
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110654129.4A Active CN113341813B (en) | 2021-06-11 | 2021-06-11 | Urban gas medium-low pressure pipe network detection method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113341813B (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113757566A (en) * | 2021-09-16 | 2021-12-07 | 上海天麦能源科技有限公司 | Control method for intelligent instrument of urban gas pipe network |
| CN113778685A (en) * | 2021-09-16 | 2021-12-10 | 上海天麦能源科技有限公司 | Unloading method for urban gas pipe network edge computing system |
| CN113935439A (en) * | 2021-12-15 | 2022-01-14 | 阿里云计算有限公司 | Fault detection method, equipment, server and storage medium for drainage pipe network |
| CN114037113A (en) * | 2021-09-24 | 2022-02-11 | 清华大学 | Intelligent water meter control method, device and system, storage medium and cloud computing center |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN203849605U (en) * | 2014-05-14 | 2014-09-24 | 锦瀚智慧管网技术有限公司 | Smart pipe network |
| CN105373110A (en) * | 2015-12-16 | 2016-03-02 | 浙江中烟工业有限责任公司 | Cigarette superspeed film packaging machine multi-loading-condition production process on-line monitoring and fault diagnosis method |
| US9599531B1 (en) * | 2015-12-21 | 2017-03-21 | International Business Machines Corporation | Topological connectivity and relative distances from temporal sensor measurements of physical delivery system |
| CN107817098A (en) * | 2017-10-12 | 2018-03-20 | 东北电力大学 | A kind of Mechanical Failure of HV Circuit Breaker diagnostic method |
| CN108006440A (en) * | 2017-12-08 | 2018-05-08 | 成都星协科技有限公司 | Distributed gas leak detection system |
| CN108343844A (en) * | 2017-01-24 | 2018-07-31 | 中国石油化工股份有限公司 | A kind of Multi-parameter modularized oil-gas pipeline safety monitoring system and method |
| CN110225075A (en) * | 2019-03-25 | 2019-09-10 | 北京快电科技有限公司 | A kind of building energy internet wisdom operation cloud operating system |
| CN110444000A (en) * | 2019-08-09 | 2019-11-12 | 贵安新区配售电有限公司 | A kind of multilist measurement data acquisition method and system based on technology of Internet of things |
| CN111552609A (en) * | 2020-04-12 | 2020-08-18 | 西安电子科技大学 | Abnormal state detection method, system, storage medium, program and server |
| CN112650195A (en) * | 2020-12-16 | 2021-04-13 | 北京航天智造科技发展有限公司 | Equipment fault maintenance method and device based on cloud edge cooperation |
-
2021
- 2021-06-11 CN CN202110654129.4A patent/CN113341813B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN203849605U (en) * | 2014-05-14 | 2014-09-24 | 锦瀚智慧管网技术有限公司 | Smart pipe network |
| CN105373110A (en) * | 2015-12-16 | 2016-03-02 | 浙江中烟工业有限责任公司 | Cigarette superspeed film packaging machine multi-loading-condition production process on-line monitoring and fault diagnosis method |
| US9599531B1 (en) * | 2015-12-21 | 2017-03-21 | International Business Machines Corporation | Topological connectivity and relative distances from temporal sensor measurements of physical delivery system |
| CN108343844A (en) * | 2017-01-24 | 2018-07-31 | 中国石油化工股份有限公司 | A kind of Multi-parameter modularized oil-gas pipeline safety monitoring system and method |
| CN107817098A (en) * | 2017-10-12 | 2018-03-20 | 东北电力大学 | A kind of Mechanical Failure of HV Circuit Breaker diagnostic method |
| CN108006440A (en) * | 2017-12-08 | 2018-05-08 | 成都星协科技有限公司 | Distributed gas leak detection system |
| CN110225075A (en) * | 2019-03-25 | 2019-09-10 | 北京快电科技有限公司 | A kind of building energy internet wisdom operation cloud operating system |
| CN110444000A (en) * | 2019-08-09 | 2019-11-12 | 贵安新区配售电有限公司 | A kind of multilist measurement data acquisition method and system based on technology of Internet of things |
| CN111552609A (en) * | 2020-04-12 | 2020-08-18 | 西安电子科技大学 | Abnormal state detection method, system, storage medium, program and server |
| CN112650195A (en) * | 2020-12-16 | 2021-04-13 | 北京航天智造科技发展有限公司 | Equipment fault maintenance method and device based on cloud edge cooperation |
Non-Patent Citations (1)
| Title |
|---|
| 董绍华等: "全球油气管道完整性技术与管理的最新进展――中国管道完整性管理的发展对策", 《油气储运》 * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113757566A (en) * | 2021-09-16 | 2021-12-07 | 上海天麦能源科技有限公司 | Control method for intelligent instrument of urban gas pipe network |
| CN113778685A (en) * | 2021-09-16 | 2021-12-10 | 上海天麦能源科技有限公司 | Unloading method for urban gas pipe network edge computing system |
| CN114037113A (en) * | 2021-09-24 | 2022-02-11 | 清华大学 | Intelligent water meter control method, device and system, storage medium and cloud computing center |
| CN113935439A (en) * | 2021-12-15 | 2022-01-14 | 阿里云计算有限公司 | Fault detection method, equipment, server and storage medium for drainage pipe network |
| CN113935439B (en) * | 2021-12-15 | 2022-05-06 | 阿里云计算有限公司 | Fault detection method, equipment, server and storage medium for drainage pipe network |
| WO2023109370A1 (en) * | 2021-12-15 | 2023-06-22 | 阿里云计算有限公司 | Fault detection method and equipment for drainage pipe network, server, and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113341813B (en) | 2022-11-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113341813B (en) | Urban gas medium-low pressure pipe network detection method and system | |
| CN108418841B (en) | Next-generation key message infrastructure network Security Situation Awareness Systems based on AI | |
| WO2011073613A1 (en) | A method, apparatus and computer program for diagnosing a mode of operation of a machine | |
| US20150241304A1 (en) | Method for the computer-assisted monitoring of the operation of a technical system, particularly of an electrical energy-generating installation | |
| CN101135614A (en) | Anomaly monitoring device and method | |
| CN114645844B (en) | Method, computing device and computer medium for determining flow state of air compression station | |
| CN109507992B (en) | Method, device and equipment for predicting faults of locomotive brake system components | |
| MX2012012377A (en) | Device and method for transmitting measurement signals in spatially extensive supply networks. | |
| EP4131094A1 (en) | Prediction method and apparatus, readable medium, and electronic device | |
| CN110570013A (en) | Single-station online wave period data prediction diagnosis method | |
| CN115792457A (en) | Method and system for diagnosing and analyzing station acquisition fault based on edge calculation | |
| CN113721182B (en) | Method and system for evaluating reliability of online performance monitoring result of power transformer | |
| CN115308465A (en) | Power supply potential safety hazard intelligent diagnosis system and method based on BP-SOM combined neural network | |
| CN111210083A (en) | Pipe network abnormity analysis method | |
| CN116951328B (en) | Intelligent drainage pipeline operation monitoring system based on big data | |
| CN113032239A (en) | Risk prompting method and device, electronic equipment and storage medium | |
| CN110399926B (en) | Street lamp fault diagnosis method and device | |
| CN112731022A (en) | Photovoltaic inverter fault detection method, device and medium | |
| CN116363843A (en) | Laboratory equipment early warning system | |
| CN116307700A (en) | Electric power system and risk assessment device and method thereof | |
| CN111314110A (en) | Fault early warning method for distributed system | |
| CN112231624B (en) | Real-time evaluation system for short-circuit resistance of multi-transformer winding based on Internet of things | |
| CN109308169A (en) | Data storage method and device and air conditioner adopting same | |
| CN110321527B (en) | Data validity judging method based on multi-element basic information fusion | |
| CN113300918A (en) | Fault detection method of intelligent lamp pole, terminal device and storage medium |
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 |