CN110866323A - Decision-making device and method for arranging sensing elements in fluid transmission and distribution pipeline network - Google Patents
Decision-making device and method for arranging sensing elements in fluid transmission and distribution pipeline network Download PDFInfo
- Publication number
- CN110866323A CN110866323A CN201811109211.3A CN201811109211A CN110866323A CN 110866323 A CN110866323 A CN 110866323A CN 201811109211 A CN201811109211 A CN 201811109211A CN 110866323 A CN110866323 A CN 110866323A
- Authority
- CN
- China
- Prior art keywords
- fluid
- sensing element
- pipeline
- decision
- deployment
- 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.)
- Pending
Links
- 239000012530 fluid Substances 0.000 title claims abstract description 71
- 238000000034 method Methods 0.000 title claims abstract description 24
- 238000009826 distribution Methods 0.000 title claims abstract description 14
- 230000005540 biological transmission Effects 0.000 title description 7
- 238000010801 machine learning Methods 0.000 claims abstract description 21
- 238000012384 transportation and delivery Methods 0.000 claims abstract description 10
- 230000006866 deterioration Effects 0.000 claims abstract description 5
- 238000006073 displacement reaction Methods 0.000 claims abstract description 4
- 238000007726 management method Methods 0.000 claims description 21
- 238000003860 storage Methods 0.000 claims description 12
- 238000004422 calculation algorithm Methods 0.000 claims description 8
- 238000004519 manufacturing process Methods 0.000 claims description 5
- 238000004088 simulation Methods 0.000 abstract description 16
- 238000001514 detection method Methods 0.000 abstract description 6
- 230000007246 mechanism Effects 0.000 abstract description 4
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 29
- 238000012549 training Methods 0.000 description 20
- 230000008859 change Effects 0.000 description 7
- 210000002569 neuron Anatomy 0.000 description 7
- 238000004364 calculation method Methods 0.000 description 6
- 238000010276 construction Methods 0.000 description 5
- 238000013528 artificial neural network Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 239000008400 supply water Substances 0.000 description 4
- 230000000694 effects Effects 0.000 description 3
- 230000002411 adverse Effects 0.000 description 2
- 238000013459 approach Methods 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 239000007788 liquid Substances 0.000 description 2
- 238000012423 maintenance Methods 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 238000003012 network analysis Methods 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 239000000126 substance Substances 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000032683 aging Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 210000004027 cell Anatomy 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000013439 planning Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
Abstract
A device and method for decision-making for the arrangement of sensing elements in a fluid delivery and distribution pipeline network. The method comprises the following steps: establishing a fluid pipe network model, wherein the fluid pipe network model comprises at least one fluid pipeline; disposing at least one sensing element in the fluid lines; simulating at least one state of leakage, blockage, displacement, deformation or deterioration of the fluid pipeline, and obtaining the simulation value of each sensing element; based on the simulated values of these sensing elements, the true deployment settings of the sensing elements are evaluated by a convergence mechanism of machine learning. Therefore, the optimal arrangement position, type and number of the sensing elements can be found out quickly, simply and conveniently, the method is more suitable for pipeline leakage detection, source tracing or blockage detection and the like, and the problems can be positioned more quickly and effectively eliminated.
Description
Technical Field
The present invention relates to a machine learning technique and a problem location estimation and inspection technique for a pipeline network, and more particularly, to a device and a method for making a decision for the arrangement of sensing elements in a fluid transmission and distribution pipeline network.
Background
The planning and construction of water, oil, gas and other fluid pipeline networks are the symbols of the progress of modern civilization and are also the important basis of urban development. The various energy sources such as water, oil and gas not only promote the prosperity and progress of industry and commerce, but also are closely related to the daily clothes, sports and recreation of the people. Therefore, the supply, delivery, distribution, testing, and management of these fluid substances has been an important issue for governments or operators. Such fluid substances, in liquid or gaseous form, are transmitted and distributed between sources, relays, transfer points, storage stations or clients of each supply via a complex network of pipelines. Generally, operators pay enormous expenses every year to arrange many precise and expensive sensing elements such as gauges, pressure gauges, flow meters, mass meters and the like in a pipeline network for monitoring and management of supply, delivery and distribution. In addition to the desire to achieve the most efficient distribution, utilization and effective management of limited resources, operators also desire to be able to deal with problems and obstacles as soon as possible when problems occur in pipelines, so as to reduce the phenomena of leakage, blockage, cause or deterioration of the pipe network due to various reasons such as poor construction, pipe aging and abnormal pipe pressure, which causes huge economic loss and inconvenience in life.
However, conventionally, there is no clear principle or reference for the arrangement of these sensing elements, and operators are often only experienced to be at their disposal at the source or the terminal of the pipeline network. Meanwhile, when the operator tests whether the installation position of the sensing element is suitable, the operator not only needs to perform construction to consume time and money, but also can damage the existing pipeline network to generate adverse effects. In addition, the built sensing devices often cannot measure the flow status of the pipeline network due to their insufficient number. Or, the operator has to build some unnecessary devices, which causes waste, and the extra devices cannot be guaranteed to bring better measurement effect. It can be seen that the above prior art has many drawbacks, and is not a good design, and needs to be improved.
Disclosure of Invention
In view of the above, the present invention provides a device and a method for determining the deployment of sensing elements in a fluid transmission and distribution pipeline network, which determine whether each pipeline converges based on a convergence mechanism of machine learning, so as to serve as a deployment basis for sensing elements in an actual pipeline network.
The invention relates to a method for making a decision for a sensing element in a fluid delivery and distribution pipeline network, which comprises the following steps. A fluid piping network model is established, and the fluid piping network model includes at least one fluid line. At least one sensing element is disposed in the fluid lines. At least one state of the fluid pipeline is simulated, and the simulated value of each sensing element is obtained according to the at least one state. The configuration settings of the sensing elements are determined based on the analog values of the sensing elements.
In another aspect, the present invention is directed to a device for decision-making for deployment of sensing elements in a fluid delivery line network, comprising a memory and a processor. The memory records a plurality of modules. A processor is coupled to the storage and accesses and loads the plurality of modules recorded by the storage. The modules comprise a model building module, a sensing element management module, a state management module and a decision module. The model building module builds a fluid piping network model, and the fluid piping network model includes at least one fluid line. The sensing element management module disposes at least one sensing element in the fluid lines. The state management module simulates at least one state of the fluid pipelines and obtains the analog value of each sensing element according to the state. The decision module decides the configuration setting of the sensing element based on the analog value of the sensing element.
Based on the above, the device and the method for decision establishment of the sensing element in the fluid transmission and distribution pipeline network in the embodiments of the present invention utilize pipe network simulation analysis software to establish a fluid pipe network model, and then model or parameters of pipeline variables such as leakage or blockage which can change the state of the pipe network are added at intervals of each section of pipeline in the fluid pipe network model in turn for simulation calculation. Then, in the simulation process in which various pipeline factors occur in each section of pipeline and at different positions, the embodiment of the present invention obtains the analog values of the sensing elements such as the pressure gauge and the flow meter, which are built in advance. These analog values are introduced into the machine learning calculation in sections, so as to train the cause estimation model and estimate the position of the state cause for each section of pipeline. The convergence of these estimates to the expected values can determine whether the learning training is completed. The configuration setting (convergence result reaching convergence standard) after learning training can be used as the basis of the actual pipeline network for configuring the sensing element, so as to obtain the optimal configuration position.
In order to make the aforementioned and other features and advantages of the invention more comprehensible, embodiments accompanied with figures are described in detail below.
Drawings
FIG. 1 is a block diagram of a deployment decision device according to an embodiment of the present invention.
FIG. 2 is a flow chart of a method of making a decision according to an embodiment of the invention.
FIG. 3 is an exemplary illustrative fluid piping model.
FIG. 4 is a schematic diagram of a machine learning-neural network algorithm, according to an embodiment of the present invention.
Description of the symbols
1: arrangement decision-making device
11: storage device
111: model building module
113: state management module
115: sensing element management module
117: decision module
13: processor with a memory having a plurality of memory cells
S210-S290: step (ii) of
301: pipeline
302: node point
303: reservoir and water source
304: water pump
305: water valve
306: water tower and water tank
307: built-up flowmeter
308: built-up water pressure meter
309: pseudo-built flowmeter
310: pseudo-built flowmeter
311: model of water leakage point
401: input layer neurons
402: hidden layer neurons
403: input layer neurons
404: weighted value chaining
405: bias weight value
406: built-in sensing element analog value input
407: analog value input of proposed sensing element
408: and outputting an estimated value.
Detailed Description
Fig. 1 is a block diagram of an arrangement decision apparatus 1 according to an embodiment of the present invention. Referring to fig. 1, the deployment decision device 1 includes at least, but not limited to, a storage 11 and a processor 13. The deployment decision device 1 may be a computing device such as a smart phone, a tablet computer, a desktop computer, a notebook computer, a server, and the like.
The storage 11 may be any type of fixed or removable Random Access Memory (RAM), Read Only Memory (ROM), flash Memory (flash Memory), Hard disk Drive (Hard disk Drive, HDD), Solid State Drive (SSD), or the like, and is used to record program codes, software modules (e.g., the model building module 111, the State management module 113, the sensing element management module 115, the decision module 117, etc.), a fluid network model, simulation values, machine learning algorithm software, deployment settings (including setting positions, quantities, types, etc.), and other data or files, which will be described in detail in the following embodiments.
The processor 13 is coupled to the storage 11, and the processor 13 may be a Central Processing Unit (CPU), a microcontroller, a programmable controller, an application specific integrated circuit, a chip, or other similar components, or a combination thereof. In the present embodiment, the processor 13 executes all operations of the deployment decision device 1, and the processor 13 can access and load those software modules recorded in the storage 11.
To facilitate understanding of the operation flow of the embodiments of the present invention, a plurality of embodiments will be listed below to describe in detail the flow of the present invention for the establishment decision of the sensing element in the fluid delivery line network. Hereinafter, the method according to the embodiment of the present invention will be described with reference to various devices, components and modules in the decision device 1. The various processes of the method may be adapted according to the implementation, and are not limited thereto.
FIG. 2 is a flow chart of a method of making a decision according to an embodiment of the invention. Referring to fig. 2, first, the model building module 111 builds a fluid pipeline model according to the actual fluid pipeline network state value information (step S210), where the fluid pipeline model includes one or more fluid pipelines. Specifically, due to the development of theory and the progress of science and technology, the current fluid pipeline network analysis and management can adopt pipe network simulation analysis software to establish a pipe network model on a computer system. For example, the U.S. Environmental Protection Agency (EPA) has developed waterworks network hydraulics and water quality simulation analysis software EPANET to assist utilities and consultants in maintenance management and water quality improvement of water supply systems. This tool is often used as a computational engine for water conservancy network analysis. And the analysis of the gas pipe network can adopt various commercial pipe network analysis software such as PIPEFLOW and the like. In other words, the model building module 111 of the present embodiment generates a fluid pipe network model by software simulation, and the fluid pipe network model may be the same as the actual pipeline network or may vary according to actual requirements.
For example, fig. 3 is an example of a fluid piping network model. Referring to fig. 3, a plurality of supply water distribution pipes 301 are used to connect a plurality of water sources 303, via supply water connection points or output nodes 302, supply water pressure control devices 304, and supply water flow or direction control devices 305, and finally to a water storage facility 306.
Next, in the training data generation stage (step S230), the state management module 113 alternately adds pipeline problems such as leakage, blockage, replacement, displacement, deformation or deterioration at the pipeline interval positions to change the state to manufacture or generate pipeline factors, so as to simulate at least one state of the fluid pipeline (step S231) (each state may include a single type or multiple types of pipeline factors, and parameters (e.g., position, size, strength, type, etc.) of each pipeline factor may be adjusted), and obtains simulated values such as a water meter, a water pressure meter, a differential pressure meter, a flow rate meter, a water quality meter, a thermometer, a gas meter, an oil meter, or other sensing elements as measuring the flow state of gas or liquid (step S233). Taking fig. 3 as an example, the state management module 113 may add a water leakage point model 311 at an interval position of the water supply pipeline, and may extract the simulation values of the established water flow sensing elements 207 and the established water pressure sensing elements 208 on the water supply pipeline after calculation by the pipeline network simulation analysis software.
Next, the decision module 117 performs machine learning training on each segment of the fluid pipeline (step S250). Machine learning is an artificial intelligence technique, which is a computer algorithm method that automatically analyzes rules from existing experiences by using a mathematical optimization method and high-speed computer algorithm, and predicts unknown data. The training process of machine learning mainly utilizes a calculation method to automatically change parameter values in a machine learning model so as to enable an estimated value to approach an expected value. In addition, by means of the error convergence value (i.e. convergence result) between the estimated value and the expected value of the model, it can be determined whether the learning training is completed (the convergence result is completed when being smaller than the convergence criterion; the convergence result is not smaller than the convergence criterion, i.e. is not completed).
The purpose of the sensor is to effectively detect the state and change of the fluid line network. Therefore, when any section of pipeline takes the actual position of the pipeline variable as the expected output under the preset sensor element configuration condition, and the corresponding sensor element simulation value is taken as the input, and is led into the machine learning model aiming at the variable position to estimate the variable position, but the set convergence standard can not be met, namely the preset sensor element configuration condition shows that the set sensor element configuration (or configuration) of the section of pipeline is bad, so that the monitoring data can not be effectively used. When the learning training of any section of pipeline still can not meet the convergence standard under the condition of the specified learning training times or time (the time or the time for estimating the position of the estimated cause of each pipeline exceeds the threshold value), the position of the sensing element can be changed or a new sensing element can be deployed. In other words, the sensing element management module 115 may adjust the layout positions of the sensing elements in the pipe network models, add new sensing elements or change types (i.e., change or adjust the layout settings of the sensing elements) (step S270). Each pipeline segment will be added with the pipeline factor again and the simulation calculation is repeated to obtain the new simulation value after the sensing element is changed. Next, the decision module 117 re-imports the new simulation values into the machine learning algorithm to perform the learning training and adjust the configuration settings of the sensing elements accordingly until the variation position estimates of all the fluid pipelines reach the convergence standard of the machine learning training (e.g., the convergence result is smaller than the convergence standard, and the convergence result is determined based on the difference between the actual position of the pipeline variation and the estimated variation position) (step S270). At this time, the position of the sensing element of the pipe network model can be used as a decision basis for the actual construction and deployment of the sensing element in the fluid transmission and distribution pipe network (step S290). In other words, the decision module 117 decides the deployment settings of the sensing elements based on the simulated values of those sensing elements through a convergence mechanism of machine learning.
Taking fig. 3 as an example, the decision module 117 uses the position of each water leakage point model 311 and the reading data of the corresponding sensing elements 307 and 308 as the input information for the machine learning training and the factor position estimation of the next stage. The decision module 117 then adds or changes a plurality of sensing elements to be built (e.g., the proposed water flow sensing element 309 and the proposed water pressure sensing element 310, i.e., adjusting the configuration settings of the sensing elements) according to the convergence value (or convergence result) of the learning training of the decision machine learning. Based on the adjusted configuration setting of the sensing element, the determining module 117 performs calculation again through the pipe network simulation analysis software to obtain a new simulation value of the sensing element in the water supply pipe network after the sensing element is reconfigured, and continues the subsequent learning and training process until the machine learning and training values estimated from the position of the water leakage point (the position of the pipeline variable factor) of each section of pipeline all reach the convergence standard, so as to use the type, the number, and the position (i.e., the configuration setting) of the sensing element at this time as the decision basis for configuration.
More specifically, when a fluid pipeline in a pipeline network is subjected to learning training of machine learning to estimate the leakage point position (i.e., estimate the cause position), the Mean Square Error (MSE) convergence value of about 10^ -1 is not easy to reconverge, and thus the training convergence standard (which can be adjusted according to actual requirements) set to be less than 10^ -3 is not achieved. The foregoing results are due to the fact that the use of sensing elements such as pressure gauges and flow meters built in the past is insufficient to sense the location of a leak in the section of piping. Therefore, the sensing element management 115 may add a flowmeter to the end of the pipeline, and reintroduce the measurement values of the added and existing sensing elements into the machine learning software for learning and training of leak estimation. If all pipelines can meet the convergence standard that the MSE qualified in training is less than 10^ -3, the convergence standard represents that the state change of the pipeline network can be effectively sensed for the configuration position of the sensing element at present, and the convergence standard is suitable for being used as the actual configuration position of the sensing element in the actual pipeline network.
Fig. 4 is a schematic diagram of a neural network algorithm of a kind in the machine learning algorithm. Please refer to fig. 3 and fig. 4. The decision module 117 inputs the analog values of the built sensing elements 307 and the analog values of the proposed sensing elements 308 read in the previous stage into the input layer neurons 401 of the neural network, and then passes through the weighted value chain 404. The decision module 117 may weight the values of the simulated sensor element readings 407 and transmit them to the hidden layer neuron 402 and the output layer neuron 403, and the neurons may produce deviation values by the deviation values 405. The neural network learning training is performed by iteratively adjusting the weight chain 404 and the bias 405 values (i.e., the convergence result is not converged or is adjusted according to the convergence result) repeatedly by an optimization method to reduce the estimated value output 408 to approach the expected output value corresponding to the input variation position. The decision module 117 may use a Mean Squared Error (MSE) of the estimated and expected outputs less than a specified value as a convergence criterion for the learning training.
In summary, the embodiments of the present invention adopt a convergence mechanism of pipe network simulation and machine learning, so as to intelligently, quickly and effectively find out the optimal configuration type, number and position of the sensing elements in the fluid pipeline network. In addition, the embodiment of the invention can effectively reduce the number of the sensing elements such as pressure gauges, flow meters and the like, so as to reduce the construction cost of physical equipment. The embodiment of the invention can not damage or generate any adverse effect on the actual fluid transmission and distribution pipeline network, and can be simultaneously used for solving the problems of leakage detection, source tracing or blockage detection and the like of the pipeline network. The embodiment of the invention can be used for solving the problems of leakage detection, source tracing or blockage detection and the like of the fluid pipeline network of water, oil, gas and the like so as to achieve the benefits of time effectiveness, saving, tracing, maintenance and management.
Although the present invention has been disclosed by way of examples, it is not intended to limit the present invention, and persons having ordinary skill in the art should make variations and modifications without departing from the spirit and scope of the present invention.
Claims (10)
1. A method of making a decision for deployment of a sensing element in a fluid delivery pipeline network, comprising:
establishing a fluid piping network model, wherein the fluid piping network model comprises at least one fluid line;
disposing at least one sensing element in the at least one fluid line;
simulating at least one state of the at least one fluid line, and accordingly obtaining a simulated value of the at least one sensing element; and
determining a deployment setting of the at least one sensing element based on the analog value of the at least one sensing element.
2. The method of claim 1, wherein the at least one condition is derived from at least one pipeline factor and the step of determining the deployment setting of the at least one sensing element based on the analog value of the at least one sensing element comprises:
taking the actual position of the at least one pipeline factor as an expected output and correspondingly taking the analog value of the at least one sensing element as an input, and estimating the estimated factor position of the at least one pipeline factor through a factor estimation model of a machine learning algorithm;
judging a convergence result according to the actual position of the at least one pipeline variable and the at least one estimated variable position; and
and judging whether the convergence result converges to adjust the configuration setting of the at least one sensing element.
3. The method of claim 2, wherein the at least one fluid line comprises a plurality of fluid lines, and wherein the step of determining whether the convergence results converge to adjust the factor estimation model further comprises:
and if the convergence result of each fluid pipeline converges, setting the current layout of the at least one sensing element as the layout basis of the actual pipeline network, wherein the layout setting comprises setting positions, quantity and types.
4. The method of claim 2, wherein the step of adjusting the deployment settings of the at least one sensing element is followed by the step of:
changing a configuration setting of the at least one sensing element if the time or number of estimates of the at least one estimated cause location exceeds a threshold but fails to converge.
5. The method of making a decision for a sensing element in a fluid delivery line network of claim 2, wherein the step of simulating said at least one condition of said at least one fluid conduit comprises:
and adding at least one pipeline factor of leakage, blockage, replacement, displacement, deformation or deterioration into the at least one fluid pipeline through pipeline network analysis software.
6. A decision-making device for deployment of sensing elements in a fluid delivery pipeline network, comprising:
a storage that records a plurality of modules; and
a processor coupled to the storage and accessing and loading the plurality of modules recorded by the storage, the plurality of modules comprising:
a model building module that builds a fluid piping model, wherein the fluid piping model comprises at least one fluid line;
a sensing element management module to dispose at least one sensing element in the at least one fluid line;
a state management module for simulating at least one state of the at least one fluid pipeline and obtaining an analog value of the at least one sensing element; and
a decision module that decides a deployment setting of the at least one sensing element based on the analog value of the at least one sensing element.
7. The device of claim 6, wherein the at least one state is derived from at least one pipeline variable, and the decision module takes an actual location of the at least one pipeline variable as an expected output and correspondingly takes a simulated value of the at least one sensing element as an input, estimates an estimated variable location of the at least one pipeline variable by a variable estimation model trained based on a machine learning algorithm, determines a convergence result according to the actual location of the at least one pipeline variable and the at least one estimated variable location, and determines whether the convergence result converges to adjust the configuration setting of the at least one sensing element.
8. The deployment decision-making apparatus for sensing elements within a fluid delivery and distribution pipeline network of claim 7, wherein said at least one fluid conduit comprises a plurality of said fluid conduits, and if the convergence of each of said fluid conduits converges, said decision module regards the current deployment of said at least one sensing element as the deployment basis for the actual pipeline network, wherein said deployment decisions include placement location, number and type.
9. The apparatus of claim 7, wherein the sensor element management module changes the configuration settings of the at least one sensor element if the time or number of estimates of the at least one estimated cause location exceeds a threshold but fails to converge.
10. The device of claim 7, wherein the model building module incorporates into the at least one fluid conduit at least one of a leak, an occlusion, a displacement, a deformation, or a deterioration of the conduit via a conduit analysis software.
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| TW107127498A TWI725333B (en) | 2018-08-07 | 2018-08-07 | Deployment decision apparatus and method thereof for sensing elements in fluid distribution pipeline |
| TW107127498 | 2018-08-07 |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110866323A true CN110866323A (en) | 2020-03-06 |
Family
ID=69651896
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811109211.3A Pending CN110866323A (en) | 2018-08-07 | 2018-09-21 | Decision-making device and method for arranging sensing elements in fluid transmission and distribution pipeline network |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN110866323A (en) |
| TW (1) | TWI725333B (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106740457A (en) * | 2016-12-07 | 2017-05-31 | 镇江市高等专科学校 | Vehicle lane-changing decision-making technique based on BP neural network model |
| CN107145723A (en) * | 2017-04-25 | 2017-09-08 | 四川省肿瘤医院 | Hospital process management system based on artificial neural network |
| EP3267173A1 (en) * | 2016-07-08 | 2018-01-10 | SUEZ Groupe | An improved system for estimating water flows at the boundaries of a sub-network of a water distribution network |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101710353B (en) * | 2009-12-03 | 2012-01-25 | 深圳先进技术研究院 | Underground pipe network laying method based on three-dimensional virtual city |
| CA2842824C (en) * | 2011-07-26 | 2023-03-14 | General Electric Company | Wastewater treatment plant online monitoring and control |
| CN103839190A (en) * | 2014-02-19 | 2014-06-04 | 清华大学深圳研究生院 | Pipe network node flow measuring and dispatching method based on pressure monitoring |
| CN104453794B (en) * | 2014-11-20 | 2017-05-17 | 中国科学院广州能源研究所 | Simulation experiment system for whole process of natural gas hydrate exploitation and simulation method |
-
2018
- 2018-08-07 TW TW107127498A patent/TWI725333B/en active
- 2018-09-21 CN CN201811109211.3A patent/CN110866323A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP3267173A1 (en) * | 2016-07-08 | 2018-01-10 | SUEZ Groupe | An improved system for estimating water flows at the boundaries of a sub-network of a water distribution network |
| CN106740457A (en) * | 2016-12-07 | 2017-05-31 | 镇江市高等专科学校 | Vehicle lane-changing decision-making technique based on BP neural network model |
| CN107145723A (en) * | 2017-04-25 | 2017-09-08 | 四川省肿瘤医院 | Hospital process management system based on artificial neural network |
Also Published As
| Publication number | Publication date |
|---|---|
| TWI725333B (en) | 2021-04-21 |
| TW202008280A (en) | 2020-02-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108591836B (en) | Method and device for detecting pipeline leakage | |
| Sarrate et al. | Sensor placement for leak detection and location in water distribution networks | |
| Preis et al. | Efficient hydraulic state estimation technique using reduced models of urban water networks | |
| Sanz et al. | Sensitivity analysis for sampling design and demand calibration in water distribution networks using the singular value decomposition | |
| CN107869653B (en) | Pipeline flow sensitivity matrix leakage detection method | |
| Tao et al. | Burst detection using an artificial immune network in water-distribution systems | |
| CN101379271A (en) | Methods, systems, and computer-readable media for real-time oil and gas field production optimization using a proxy simulator | |
| US11906987B2 (en) | Pressure control in a supply grid | |
| EP3800323A1 (en) | Virtual flow meter method and system for monitoring flow of an oil well in an industrial environment | |
| CN111664823A (en) | Method for detecting thickness of scale layer of voltage-sharing electrode based on difference of medium heat conduction coefficients | |
| Kutyłowska | Prediction of failure frequency of water-pipe network in the selected city | |
| Meseguer et al. | Model-based monitoring techniques for leakage localization in distribution water networks | |
| Rojek et al. | Comparison of different types of neuronal nets for failures location within water-supply networks | |
| Shravani et al. | A machine learning approach to water leak localization | |
| CN113486950B (en) | Intelligent pipe network water leakage detection method and system | |
| CN110866323A (en) | Decision-making device and method for arranging sensing elements in fluid transmission and distribution pipeline network | |
| Kallesøe et al. | Self calibrating flow estimation in waste water pumping stations | |
| CN116484219A (en) | Water supply network water quality abnormal pollution source identification method based on gate control graph neural network | |
| Shravani et al. | Cloud-based water leakage detection and localization | |
| Kemba et al. | Leakage detection in Tsumeb east water distribution network using EPANET and support vector regression | |
| Sánchez-Rivero et al. | A Novel Approach for Leak Localization in Water Distribution Networks Using Computational Intelligence | |
| CN112097125B (en) | Water supply pipe network pipe burst detection and positioning method based on self-adaptive checking | |
| CN111563332B (en) | Urban water supply pipe network leakage positioning method based on night pressure regulation actual measurement | |
| CN110705186B (en) | Real-time online instrument checksum diagnosis method through RBF particle swarm optimization algorithm | |
| US20220196512A1 (en) | Detection of a leakage in a supply grid |
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 |