CN113906280A - Method and apparatus for operating a distribution network - Google Patents
Method and apparatus for operating a distribution network Download PDFInfo
- Publication number
- CN113906280A CN113906280A CN201980095885.9A CN201980095885A CN113906280A CN 113906280 A CN113906280 A CN 113906280A CN 201980095885 A CN201980095885 A CN 201980095885A CN 113906280 A CN113906280 A CN 113906280A
- Authority
- CN
- China
- Prior art keywords
- distribution network
- transient event
- network
- sensors
- model
- 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
- 238000000034 method Methods 0.000 title claims abstract description 62
- 230000001052 transient effect Effects 0.000 claims abstract description 110
- 230000009471 action Effects 0.000 claims abstract description 21
- 238000005259 measurement Methods 0.000 claims abstract description 21
- 239000013598 vector Substances 0.000 claims description 24
- 230000036962 time dependent Effects 0.000 claims description 11
- 239000000463 material Substances 0.000 claims description 8
- 238000007477 logistic regression Methods 0.000 claims description 6
- 238000012545 processing Methods 0.000 claims description 6
- 239000000126 substance Substances 0.000 claims 2
- 238000004590 computer program Methods 0.000 abstract description 8
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 8
- 230000001419 dependent effect Effects 0.000 description 6
- 238000010586 diagram Methods 0.000 description 6
- 230000006870 function Effects 0.000 description 4
- 238000009434 installation Methods 0.000 description 3
- 238000013528 artificial neural network Methods 0.000 description 2
- 230000007797 corrosion Effects 0.000 description 2
- 238000005260 corrosion Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 239000011159 matrix material Substances 0.000 description 2
- VNWKTOKETHGBQD-UHFFFAOYSA-N methane Chemical compound C VNWKTOKETHGBQD-UHFFFAOYSA-N 0.000 description 2
- 238000012552 review Methods 0.000 description 2
- 238000005070 sampling Methods 0.000 description 2
- 239000002689 soil Substances 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 230000032683 aging Effects 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 230000002238 attenuated effect Effects 0.000 description 1
- 230000015556 catabolic process Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000005094 computer simulation Methods 0.000 description 1
- 230000001186 cumulative effect Effects 0.000 description 1
- 238000006731 degradation reaction Methods 0.000 description 1
- 239000003651 drinking water Substances 0.000 description 1
- 235000020188 drinking water Nutrition 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 239000007789 gas Substances 0.000 description 1
- 238000010438 heat treatment Methods 0.000 description 1
- 239000007788 liquid Substances 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000003345 natural gas Substances 0.000 description 1
- 230000003334 potential effect Effects 0.000 description 1
- 238000001556 precipitation Methods 0.000 description 1
- 230000000644 propagated effect Effects 0.000 description 1
- 230000008439 repair process Effects 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 238000000638 solvent extraction Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 230000004083 survival effect Effects 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M3/00—Investigating fluid-tightness of structures
- G01M3/02—Investigating fluid-tightness of structures by using fluid or vacuum
- G01M3/26—Investigating fluid-tightness of structures by using fluid or vacuum by measuring rate of loss or gain of fluid, e.g. by pressure-responsive devices, by flow detectors
- G01M3/28—Investigating fluid-tightness of structures by using fluid or vacuum by measuring rate of loss or gain of fluid, e.g. by pressure-responsive devices, by flow detectors for pipes, cables or tubes; for pipe joints or seals; for valves ; for welds
- G01M3/2807—Investigating fluid-tightness of structures by using fluid or vacuum by measuring rate of loss or gain of fluid, e.g. by pressure-responsive devices, by flow detectors for pipes, cables or tubes; for pipe joints or seals; for valves ; for welds for pipes
- G01M3/2815—Investigating fluid-tightness of structures by using fluid or vacuum by measuring rate of loss or gain of fluid, e.g. by pressure-responsive devices, by flow detectors for pipes, cables or tubes; for pipe joints or seals; for valves ; for welds for pipes using pressure measurements
-
- E—FIXED CONSTRUCTIONS
- E03—WATER SUPPLY; SEWERAGE
- E03B—INSTALLATIONS OR METHODS FOR OBTAINING, COLLECTING, OR DISTRIBUTING WATER
- E03B7/00—Water main or service pipe systems
- E03B7/07—Arrangement of devices, e.g. filters, flow controls, measuring devices, siphons or valves, in the pipe systems
- E03B7/071—Arrangement of safety devices in domestic pipe systems, e.g. devices for automatic shut-off
-
- E—FIXED CONSTRUCTIONS
- E03—WATER SUPPLY; SEWERAGE
- E03B—INSTALLATIONS OR METHODS FOR OBTAINING, COLLECTING, OR DISTRIBUTING WATER
- E03B7/00—Water main or service pipe systems
- E03B7/07—Arrangement of devices, e.g. filters, flow controls, measuring devices, siphons or valves, in the pipe systems
- E03B7/075—Arrangement of devices for control of pressure or flow rate
-
- 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
- F17D5/06—Preventing, monitoring, or locating loss using electric or acoustic means
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M3/00—Investigating fluid-tightness of structures
- G01M3/02—Investigating fluid-tightness of structures by using fluid or vacuum
- G01M3/04—Investigating fluid-tightness of structures by using fluid or vacuum by detecting the presence of fluid at the leakage point
- G01M3/24—Investigating fluid-tightness of structures by using fluid or vacuum by detecting the presence of fluid at the leakage point using infrasonic, sonic, or ultrasonic vibrations
- G01M3/243—Investigating fluid-tightness of structures by using fluid or vacuum by detecting the presence of fluid at the leakage point using infrasonic, sonic, or ultrasonic vibrations for pipes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A20/00—Water conservation; Efficient water supply; Efficient water use
- Y02A20/15—Leakage reduction or detection in water storage or distribution
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Economics (AREA)
- Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Public Health (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Water Supply & Treatment (AREA)
- Tourism & Hospitality (AREA)
- Marketing (AREA)
- Hydrology & Water Resources (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Business, Economics & Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Theoretical Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Mechanical Engineering (AREA)
- Quality & Reliability (AREA)
- Educational Administration (AREA)
- Development Economics (AREA)
- Acoustics & Sound (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Fluid Mechanics (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
A method for operating a distribution network having a specific network topology using N sensors sensing wave front characteristics is proposed. Each of the N sensors is located at a particular measurement location in the distribution network. The method comprises the following steps a), b) and c): a) using at least a subset of the N sensors to obtain transient event parameter values for a particular transient event in the distribution network, b) determining a risk factor indicative of a hazard in the distribution network in dependence on the obtained transient event parameter values and actual values of network parameters indicative of the distribution network, and c) performing one of a plurality of actions at the distribution network in dependence on the determined risk factor. Furthermore, a computer program product, a device and a distribution network are proposed.
Description
Technical Field
The invention relates to a method of operating a distribution network having a specific network topology using N sensors sensing wave front characteristics, each of said N sensors being located at a specific measurement position in the distribution network. The invention also relates to a computer program product and to an apparatus for operating a distribution network having a specific network topology. Furthermore, the invention relates to a distribution network comprising a plurality of pipe segments for distributing a specific load and to such an apparatus for operating the distribution network.
Background
Distribution networks, such as water supply networks or heating networks, may fail for various reasons. For example, failure of a particular segment of a distribution network may result in a customer supply outage or damage to infrastructure (e.g., roads and other property). Therefore, there is a need to minimize the risk of failures in the distribution network, along with the task of minimizing the time required to correctly detect, locate and isolate damaged segments in the distribution network.
Conventional models and methods for assessing the risk of failure of a pipe section of a distribution network are known from references [1] to [4 ].
Disclosure of Invention
The present invention aims to enhance the operation of a distribution network.
According to a first aspect, a method for operating a distribution network having a specific network topology using N sensors sensing wave front characteristics is presented. Each of the N sensors is located at a particular measurement location in the distribution network. The method comprises the following steps a), b) and c):
a) transient event parameter values for a particular transient event in the distribution network are obtained using at least a subset of the N sensors,
b) determining a risk factor indicative of a hazard in the distribution network in dependence on the obtained transient event parameter value and an actual value of a network parameter indicative of the distribution network, an
c) One of a plurality of actions is performed at the distribution network depending on the determined risk factor.
For example, the distribution network is a water distribution network, an oil distribution network, a natural gas distribution network, or a thermal distribution network. The distribution network may also be referred to as a network.
The risk may be a real or actual damage of the distribution network, such as a pipe jam or a pipe burst, or a high probability of damage to a pipe or pipe segment in the distribution network. The pipe segments may also be referred to as segments.
Examples of transient events include leaks, valve openings, valve closings, pump starts or pump stops. Further, examples of transient event parameters include the amplitude of a particular transient event, the location of a particular transient event in the distribution network, and/or the event type of a particular transient event in the distribution network. The event type may also be referred to as a type.
Depending on the amplitude of the transient event, the wavefront caused by the transient event may be detected by a particular subset of sensors or all sensors in the distribution network. Thus, the subset of sensors is able to obtain transient event parameter values for a particular transient event. In other words, different transient events may be detected by different subsets of sensors located at different measurement locations in the distribution network.
In particular, the topology of the distribution network is known a priori, in particular before the execution of the method comprising steps a) to c). In particular, information indicative of the network topology as part of the network parameters is stored in a memory, wherein said information may be used in said step b) of the method.
Furthermore, the network parameters may include information about the lifetime of the pipes, the materials of the pipes, and the average and maximum static loads in the distribution network. Further, the network parameters may include records or historical data of the distribution network.
Performing one of the actions according to step c) may comprise providing a replacement recommendation for replacing the pipe or pipe section or providing an alarm to an operator or service person of the distribution network. Further, performing the particular action may include recording the determined risk factor or factors. Further, the recorded determined risk factors may be used to generate or trigger replacement recommendations or alerts.
Further, the particular action may include providing a visual representation of the distribution network, such as a heat map representing a graph of the distribution network and indicating potential hazards and determined risk factors, to an operator or service personnel of the distribution network.
By using not only the actual values of the network parameters but also the obtained transient event parameter values, the risk factors of the hazards in the distribution network can be determined with a higher accuracy. Determining risk factors with greater accuracy results in reduced maintenance costs for the distribution network and enhanced planning of network repair strategies.
In the following, several embodiments of a method for operating a distribution network are described.
According to an embodiment, the risk factor is determined in dependence on the obtained transient event parameter value, the actual value of the network parameter, load-related factors of the load distributed by the distribution network, and external factors describing the environment of the distribution network.
According to a further embodiment, the transient event parameters comprise the amplitude of a specific transient event, in particular at a specific measurement location or locations, the location of a specific transient event in the distribution network and/or the event type of a specific transient event in the distribution network.
According to a further embodiment, step a) comprises:
transient event parameter values for a plurality of specific transient events in the distribution network are obtained using at least the subset of the N sensors.
According to a further embodiment, step a) comprises:
sensing a wavefront characteristic caused by a particular transient event in the distribution network using at least the subset of the N sensors,
collecting signals from the subset of N sensors, the signals being indicative of sensed wavefront characteristics, an
Processing the collected signals to obtain the transient event parameters.
According to a further embodiment, step b) comprises:
providing a model for modeling a hazard in a distribution network, the model being time dependent and using a set of parameters representing at least network parameters and transient event parameters,
modeling the actual hazard by applying the determined actual values of the obtained transient event parameter values and the actual values of the network parameters of the parameter set to the provided model, an
The risk factor is determined depending on the actual risk modeled.
According to a further embodiment, step b) comprises:
the distribution network is divided into segments of pipe,
assigning each of the pipe segments to one of a plurality of M groups according to at least one classification parameter, wherein M ≧ 2, an
For each of the M groups, performing the following sub-steps i) to iii):
i) providing a model for modeling a hazard in a pipe segment of a group, the model being time dependent and using a set of parameters representing at least a network parameter and a transient event parameter,
ii) modeling the actual risk by applying the determined actual values (including at least the obtained transient event parameter values) and the actual values of the network parameters of the parameter set to the provided model, and
iii) determining a risk factor for the set of pipe sections depending on the actual risk modeled.
According to a further embodiment, the tube segments are separated from each other and each of the tube segments is homogenous at least in terms of tube material and tube diameter.
According to a further embodiment, the model used to model the actual hazard uses Cox regression.
According to a further embodiment, in the Cox-regression, the following formula is used for modeling the time-dependent and parameter set-dependent actual hazards h (t, x):
h(t,x)=h0(t)exp{βTx}... (1)
in this formula, t designates time, x designates a parameter set as a vector, h0(t) specifies the baseline hazard due to time t, and β specifies the coefficient vector of the parameter set.
According to a further embodiment, each of the sensors is a high-speed pressure sensor. For example, each of the sensors has a sampling rate of 100Hz or higher, in particular 200Hz or higher.
According to a further embodiment, the step b) of determining the risk factors is performed by a central processor unit of the distribution network.
According to a further embodiment, the method comprises the steps of: determining the location of a particular transient event in the distribution network in dependence on the difference in the detected arrival times of wavefronts detected by sensors located at the subset of measurement locations and the locations of the measurement locations.
In particular, the location of the measurement location is part of the network topology that is known a priori. Thus, the position of the measurement location is known before the above-mentioned method steps are performed.
According to a further embodiment, for each possible sensor pair of the N sensors, the time shift between the arrival times at the two sensors of the sensor pair is determined by cross-correlating the wavefronts received at the two sensors.
According to a further embodiment, the event type of the transient event in the distribution network is classified as leak, valve open, valve closed, pump start or pump stop using the determined position of the transient event in the distribution network, the detected arrival times of the wavefronts detected using the sensors located at the subset of the measurement positions, and using the specific network topology of the distribution network.
According to a further embodiment, the risk factor is determined in dependence on an actual value of a network parameter, an actual value of a load related factor of the load distributed by the distribution network comprising the obtained transient event parameter value, and an external factor describing the environment of the distribution network.
The network parameters may include meta-information including, inter alia, segment age, segment material, degree of corrosion, etc.
Load-related factors may include pressure transients and cumulative flow rates through the respective segments. In addition, external factors may include soil conditions and installation properties. For example, the installation properties may describe installation under street conditions or under heavy traffic area conditions.
The above factors may also be referred to as covariates. Covariates may be continuous, discrete or categorical. It may be noted that covariates may be converted into discrete variables or categorical variables in a manner that uses ranges.
According to a further embodiment, step b) comprises:
providing a model for modeling hazards in a distribution network, the model being time dependent and using factor vectors representing network parameters, load-related factors including transient event parameters, and external factors,
modeling the actual hazard by applying the determined actual values (including at least the obtained values of the load-related factors including the transient event parameter), the actual values of the network parameters and the actual values of the external factors of the factor vector to the provided model, and
the risk factor is determined depending on the actual risk modeled.
According to a further embodiment, step b) comprises:
partitioning a distribution network intoA plurality of interconnected pipe sectionsWhereinTo be provided withTo designate the ith tube segment, wherein the tube segments are separated from each other and each of the tube segments is homogenous at least in terms of tube material and tube diameter.
The factors may also be referred to as covariates.
According to a further embodiment, to model the life of the pipe section, a formula is used
For aligning pipe sectionsAssociated time-dependent real hazardsModeling is performed, whereinIs a factor vector, t is the segment to be evaluatedIs the coefficient vector of the model,is used to calculate a model dependent on the use (e.g. a Cox regression model or a logistic regression model)) As a function of the actual risk.
According to a further embodiment, the model for modeling the actual hazard uses a Cox regression model, wherein in the Cox regression a formula is used
Wherein h iso(t) specifies a baseline hazard due to time t.
The Cox regression model is a semi-parametric model. In particular, it quantifies the baseline risk, a risk caused in a non-parametric manner only by aging of the component (here the pipe section). It then uses a parameterized approach to accelerate or decelerate the hazard curve based on these factors.
According to a further embodiment, the model for modeling the actual hazard uses a logistic regression model, wherein in the logistic regression model, a formula is used
The logistic regression is a sigmoid function whose range is limited to the range [0, 1]]And (4) the following steps. It is therefore suitable for modeling the failure probability of a component (here a pipe segment). It is mentioned that in this model, time is also considered as a factor vectorA part of (additional covariates) and has corresponding coefficients in the vector beta. As can be seen from the above equation, the method is a parametric method whose output can be via an expectation-maximization (EM) method or an iterative re-weighted minimizationThe two-by-one (IRLS) method learns for historical data.
According to a further embodiment, the coefficient vector β is learned based on historical data. In particular, learning the hazard model means using historical data to infer the coefficient vector β. For factors such as pipe diameter and length, they are easily incorporated into the model, i.e. they only affect their corresponding segment, and not the other segments. However, transient events do affect other segments — relative to the segment on which the transient event occurred. This is because these events can generate pressure transients that propagate through the network and can be reflected by some components of the network, such as valves and/or fittings. Thus, when a transient event occurs, it may affect other parts of the network.
According to a further embodiment, the model is adapted to model reflections of transient events in the distribution network and/or the factor vector comprises factors related to different types of pressure transients. In the following, a detailed discussion will be made regarding an example of a pressure transient as an example of a transient event:
pressure transients cause fatigue, a phenomenon that accelerates the failure of pipe segment pressure transients for a variety of reasons (e.g., burst, valve operation (open and/or close), pump operation (start and/or close), etc.). Regardless of why transients occur, they propagate through pipe segments connected to the segment where the event occurred. This affects not only the segment on which the event occurs, but also the parts of the other connections with different levels of influence due to the attenuation of the amplitude of the transient wave as it propagates through the network.
In addition to the propagation of pressure transient waves, they are also reflected by parts of the network, such as valves and fittings. These reflections therefore have an impact on the ongoing risk on the network. In addition, these reflections also pass through the connected segments and are reflected again. For reasons of ease of handling, only first order reflections are considered in the following, that is to say only propagation of the original pressure transient and propagation of the first order reflections are considered. However, it is possible to relax the method to include more reflection stages.
wherein:
is a collection of all segments in which an event that occurs will affect the segment of interestAnd is
Depending on the section of interestThe distance from the rest of the segments in the network. In addition to this, the present invention is,depending on the topology of the network, since the topology gives these reflecting surfaces relative to the segment of interestThe position of (a). E.g. lookupOne way of (1) is to consider the relative segment of interestSegments and reflective surfaces whose respective distances are less than a predefined threshold.
To integrate pressure transients with a segment of interestFirst, the pressure transient is divided into l types. For example, these types may include:
i. burst of segment
Valve operation (open/close)
Pump operation (on/off)
Then, in addition to the above-described factors, the factor vectorIncluding factors related to the pressure transients that may be,
Wherein:
is to represent pressure transients as affecting the segment of interestA set of factor vectors for the covariate of (c),
Therefore, to combine different types of pressure transients with a segment of interestThe impact of transients may be considered to decay with distance traveled. To model this, a Radial Basis Function (RBF) may be used.
Wherein:
is that the section of interest is describedSection ofA propagated pressure transient occurring atThe RBF of the attenuation of the influence of,
is describing the data from the section of interestUpper surface ofReflected pressure transients of) The affected attenuated RBF.
It may be mentioned that once a wave reaches a reflecting surface, reflection occurs on the wave. That is, when the ξ -th type event is of magnitudeOccurs in sectionsWhen it is in place, it first propagates to the reflecting surfaceWhile attenuating toThen it comes from the reflecting surfaceReflect back to the section of interestAccording to reflection RBFAnd (4) attenuation.
Various RBFs may be used, one example being gaussian RBFs, the corresponding RBFs used in equation (7) being defined in equations (8), (9) and (10).
Wherein:
is from the event location over the networkTo the section of interestThe travel distance of the center coordinates of (a),
is from the event location over the networkTo the reflecting surfaceThe distance of travel of (a) is,
is derived from a reflecting surface by means of a networkTo the section of interestThe travel distance of the center coordinates of (a),
is a width parameter controlling the decay rate of the pressure transient of the ξ -th type of propagation,
is a width parameter which controls the decay rate of the ξ -th type pressure transient of the reflection.
It should be mentioned that for long segments, virtual segmentation can be used to obtain more accurate and high resolution results. More specifically, a long segment may be segmented into multiple shorter segments, making the measure of distance traveled more suitable for equations (8), (9), and (10).
Equation (7) contains the width parameterThese can be estimated based on field experiments. It is worth mentioning that equations (8), (9) and (10) describe one type of RBF, i.e. gaussian RBF, however, other types such as thin plate splines (TPS-RBF) may also be used to give examples.
Width parameterFor RBF) The influence of the result of (2), the output value O is shown in fig. 7. In FIG. 7, the distance on the x-axis is relative to the thingIn both directions of the piece position. Further, in FIG. 7, curve VI designatesCurve V2 specifiesCurve V3 specifiesAnd curve V4 specifies
Further, as an illustrative example, let us assume a hazard model with the following covariates:
1. segment material type (covariate x)1)。
2. Segment diameter (covariate x)2)。
3. Segment length (covariate x)3)。
4. Valve operation transient (covariate x)4)。
5. Pump operation transient (covariate x)5)。
6. Burst transient (covariate x)6)。
In this example, three types of pressure transients are considered, i.e., l-3. The total number of covariates is 6, so the segmentsThe covariate vector of isSo thatDoes not include time, andincluding time, defined as follows:
in equations (11) and (12), the covariates related to pressure transients may be associated with equation (7) as follows:
another measure of failure rate may be of interest, such as survival rateAnd the probability of failure.
These can be obtained from the hazard rates as follows:
further, the probability of failure may be calculated as follows:
wherein:
The present solution described thus far quantifies the risks associated with pipe segments and, therefore, networks.
Suggestions regarding mid-section replacement in the network are provided below. This raises the question of whether segments are placed and what the probability of failure is.
Since the risk can be quantified in a probabilistic manner, replacement recommendations can be considered while paying attention to the uncertainty of the failure.
And a decision tool under uncertainty is proposed. In table (1), a decision cost matrix is shown. That is, two actions (replacement, no replacement) may be taken, while two results (failure, no failure) may occur. This results in 4 possible scenarios.
Fault of | Without failure | Expected cost | |
Replacement of | A11(t) | A12(t) | p1(t)A11(t)+p2(t)A12(t) |
Is not replaced | A21(t) | A22(t) | p1(t)A21(t)+p2(t)A22(t) |
Probability of | p1(t) | p2(t) |
Table 1: decision cost matrix
Wherein:
A11(t) -is the cost of taking the action of replacing the pipe section at time t, and it actually fails at t
A12(t) -is the cost of taking the action of replacing the pipe section at time t, and it is virtually non-faulted at t
A21(t) -is the cost of taking action not to replace a pipe section at time t, and it actually fails at t
A22(t) -is the cost of taking action not to replace a pipe segment at time t, and virtually no failure at t
p1(t) -probability of pipe section failing at time t
p2(t) -probability of a pipe section not failing at time t
The expected cost per action (replacement or not) is calculated as follows:
wherein:
Is from a set of potential actions at time tTaking action ofiCost push ofThe recommended operation is an operation that minimizes the expected cost, as in equation (17):
wherein:
a*(t) -is the recommended operation at time t.
Further, in order to recommend the replacement time, the time at which the replacement expected cost becomes smaller than the non-replacement expected cost is found as in equation (18) has been solved and given as the recommended replacement time.
Wherein:
According to a second aspect, a computer program product is presented, wherein the computer program product comprises program code for performing the method of the first aspect or one of the embodiments of the first aspect, when the program code is run on at least one computer.
The computer program product, such as the computer program means, may be embodied as a memory card, a USB stick, a CD-ROM, a DVD or as a file downloadable from a server in the network. Such files may be provided, for example, by transmitting files comprising computer program products from a wireless communication network.
According to a third aspect, a device for operating a distribution network having a specific network topology is proposed. The apparatus comprises:
a plurality of N sensors for sensing wavefront characteristics, each of the N sensors being located at a particular measurement location in the distribution network, wherein at least a subset of the N sensors are configured to obtain transient event parameter values for a particular transient event in the distribution network,
a determining unit for determining a risk factor indicative of a hazard in the distribution network in dependence on the obtained transient event parameter value and an actual value of a network parameter indicative of the distribution network, an
An execution unit for executing one of a plurality of actions at the distribution network in dependence on the determined risk factor.
In particular, the apparatus may be or may include a computer-assisted or computer-related system or computer system.
The respective unit (e.g. the determining unit or the executing unit) may be implemented in hardware and/or software. If the unit is implemented in hardware, it may be implemented as a device, e.g. embodied as a computer or a processor or as part of a system, e.g. a computer system. If the unit is implemented in software, it may be embodied as a computer program product, function, routine, program code, or executable object.
Embodiments and features according to the first aspect are also embodiments of the third aspect.
Further possible implementations or alternative solutions of the invention also include combinations of features described above or below with respect to the embodiments — not explicitly mentioned here. Those skilled in the art may also add individual or isolated aspects and features to the most basic form of the invention.
Drawings
Further embodiments, features and advantages of the present invention will become apparent from the subsequent description and the dependent claims, taken in conjunction with the accompanying drawings, in which:
fig. 1 shows a sequence of method steps for a first embodiment of a method of operating a distribution network;
FIG. 2 shows a schematic diagram of an example for a distribution network;
fig. 3 shows a sequence of method steps for operating a second embodiment of a method of distributing a network;
fig. 4 shows a diagram illustrating distance dependent attenuation of transient effects with respect to a distribution network;
FIG. 5 shows a schematic block diagram of an embodiment of an apparatus for operating a distribution network;
fig. 6 shows a sequence of method steps for operating a third embodiment of a method of distributing a network; and
fig. 7 shows a diagram illustrating the effect of the width parameter on the output value in an RBF.
In the drawings, like reference numerals refer to identical or functionally equivalent elements, unless otherwise specified.
Detailed Description
In fig. 1, a sequence of method steps of a first embodiment of a method of operating a distribution network 10 having a particular network topology using sensors 31-33 for sensing high speed wavefront characteristics is shown. Each of the N sensors 31-33 is located at a particular measurement location L1-L3 in the distribution network 10. The distribution network 10 may be, for example, a water distribution network, an oil distribution network, a gas distribution network, or a heat distribution network.
In this regard, fig. 2 shows a schematic diagram of an example for a distribution network 10. In particular, fig. 2 shows only a small portion of such a distribution network 10. The distribution network 10 of fig. 2 has a plurality of tubes 20 adapted to conduct a liquid, such as water or oil.
Without loss of generality, the number N of sensors 31-33 in fig. 2 is three (N-3). Typically, N may be a positive integer, e.g., N may be greater than 1000 in a water distribution network. Each of the sensors 31-33 for detecting the transient event parameter values of a particular transient event E has a sampling rate of 100MHz or more. Thus, the sensors 31-33 are high-speed pressure sensors.
In the example of fig. 2, a burst of one of the tubes 20 is depicted as an example of a transient event E. The different paths of propagation of the pressure wave caused by the burst E are indicated in fig. 2 by P1, P2 and P3. In the example of fig. 2, the first sensor 31 is located at the measurement position L1, the second sensor 32 is located at the measurement position L2, and the third sensor 33 is located at the measurement position 33.
The embodiment of the method according to fig. 1 has the following method steps S10-S30:
in step S10, transient event parameter values for a particular transient event E in the distribution network 10 are obtained using at least a subset of the N sensors 31-33. For example, each of the subset of sensors 31-33 senses a wavefront characteristic caused by the particular transient event E. Depending on the sensed wavefront characteristics, transient event parameter values are generated or created. Examples of transient event parameters include the amplitude of a particular transient event E (in particular at the respective particular measurement positions L1-L3 of the particular sensors 31-33), the location of the particular transient event E in the distribution network 10 and/or the event type of the particular transient event E in the distribution network 10. Examples of event types include leak, congestion, valve open, valve close, pump start, and pump stop.
In step S20, a risk factor indicative of a hazard in the distribution network 10 is determined depending on the obtained transient event parameter value and the actual value of the network parameter indicative of the distribution network 10.
The network parameters may include meta-information about the distribution network 10 such as pipe life, pipe material, pipe diameter, corrosion related characteristics, and the like. Furthermore, the input parameters for determining the risk factors may include load-related factors of the load by the distribution network 10 and external factors describing the environment of the distribution network 10. External factors may include soil conditions, temperature, precipitation, etc. The load-related factors may exemplarily comprise parameters of the load itself, such as a density value of the load.
In step S30, one of a plurality of actions at the distribution network 10 is performed depending on the determined risk factor. Performing one of the actions may include providing a replacement recommendation for replacing the pipe or pipe components or providing an alert to an operator or service personnel of the distribution network 10.
Further, performing a particular action may include recording one determined risk factor or a plurality of determined risk factors over time. Furthermore, replacement recommendations or alerts may be generated or triggered based on the recorded determined risk factors.
Further, the particular action may include providing a visual representation of the distribution network 10 to an operator or service personnel of the distribution network 10, for example in the form of a heat map indicating potential hazards and risk factors of the distribution.
Fig. 3 shows a sequence of method steps for a second embodiment of a method for operating the distribution network 10. The second exemplary embodiment of fig. 3 is based on the first exemplary embodiment of fig. 1, wherein method step S10 of fig. 1 is carried out by method steps S11 to S13 according to fig. 3, and method step S20 of fig. 1 is carried out by method steps S21 to S23 according to fig. 3.
In this regard, method step S10 includes steps S11-S13:
in step S11, at least the subset of the N sensors 31-33 is used to sense the wavefront characteristics caused by a particular transient event E in the distribution network 10.
In step S12, signals from the subset of N sensors 31-33 are collected. The signal is indicative of a sensed wavefront characteristic.
In step S13, the collected signals are processed to obtain the transient event parameters. For example, the processing may be performed by a central processing unit of the distribution network 10.
As described above, method step S20 of FIG. 3 includes steps S21-S23:
in step S21, a model for modeling hazards in distribution network 10 is provided. The model is time dependent and uses a set of parameters representing at least network parameters and transient event parameters.
In step S22, the actual risk is modeled by applying the determined actual values (including at least the obtained transient event parameter values) and the actual values of the network parameters of the parameter set to the provided model.
In step S23, risk factors are determined depending on the actual risk modeled.
In particular, the step S20 may include dividing the distribution network 10 into pipe segments to distribute each of the pipe segments to one of a plurality of M groups based on at least one classification parameter (M ≧ 2). Then, the following substeps i) to iii) may be performed:
i) providing a model for modeling a hazard in a pipe segment of a group, the model being time dependent and using a set of parameters representing at least a network parameter and a transient event parameter,
ii) modeling the actual risk by applying the determined actual values (including at least the obtained transient event parameter values) and the actual values of the network parameters of the parameter set to the provided model, and
iii) determining a risk factor for the pipe sections of the group depending on the actual risk modeled.
In particular, the tube sections are separated from each other and each of the tube sections is homogenous at least in terms of tube material and tube diameter. In particular, the model uses Cox regression. In Cox regression, the formula is used
h(t,x)=h0(t)exp{βTx}...(19)
For modeling the time-dependent and parameter set-dependent actual risk h (t, x), where t specifies time, x specifies a parameter set as a vector, h0(t) specifies a baseline risk due to time, t, and β specifies a coefficient vector of the parameter set.
The parameter set x may be formulated as x ═ x1,…,xp]TWherein x ispAt least one transient event parameter, such as a pressure transient, is specified.
From said pressure transient xpThe transient event E in the distribution network 10 shown affects the portion of the distribution network 10 where it occurs the most and its effect fades away as the distance traveled increases. In the formula mentioned below, this is controlled via the exponent k, i.e. the larger k, the faster the transient effect decays with the distance traveled.
xp=Mψ...(20)
In the above equation, M specifies the magnitude of the pressure transient, and diAssigning an i-th segment S from the location of the transient event E to the distribution network 10iThe distance of the center of (c).
In this regard, fig. 4 shows a graph illustrating distance dependent attenuation with respect to dangerous transient effects in the distribution network 10. In fig. 4, the x-axis shows the distance d from the location of the transient event E in the distribution network 10 and the y-axis shows the index k of the above formula.
In fig. 4 described above, a curve C0 shows the curvature when k is 0, a curve C1 shows the curvature when k is 1, a curve C2 shows the curvature when k is 2, and a curve C3 shows the curvature when k is 3.
Furthermore, fig. 5 shows a schematic block diagram of an embodiment of a device 50 for operating the distribution network 10 as shown in fig. 2.
The apparatus 50 of fig. 5 shows a plurality 51 of sensors 31, 32, 33 for sensing wavefront characteristics. Each of the sensors 31-33 is located at a particular measurement location L1-L3 in the distribution network 10 (see FIG. 2). At least a subset of the sensors 31-33 are configured to obtain transient event parameter values for a particular transient event E in the distribution network 10 (see fig. 2).
Furthermore, the device 50 comprises a determination unit 52 and an execution unit 53.
The determination unit 52 is configured to determine a risk factor indicative of a hazard in the distribution network 10 depending on the obtained transient event parameter value and an actual value of a network parameter indicative of the distribution network 10.
The execution unit 53 is configured to perform one of a plurality of actions at the distribution network 10 depending on the determined risk factor.
Fig. 6 shows a sequence of method steps for a third embodiment of a method for operating the distribution network 10. The third exemplary embodiment of fig. 6 is based on the first exemplary embodiment of fig. 1, wherein method step S10 of fig. 1 is carried out by method steps S11 to S13 according to fig. 6, and method step S20 of fig. 1 is carried out by method steps S20a to S20c according to fig. 6.
In this regard, method step S10 includes steps S11-S13:
in step S11, at least the subset of the N sensors 31-33 is used to sense the wavefront characteristics caused by a particular transient event E in the distribution network 10.
In step S12, signals from the subset of N sensors 31-33 are collected. The signal is indicative of a sensed wavefront characteristic.
In step S13, the acquired signals are processed to obtain the transient event parameters. For example, the processing may be performed by a central processing unit of the distribution network 10.
As described above, method step S20 of FIG. 6 includes steps S20a-S20 c:
in step S20a, a model for modeling hazards in distribution network 10 is provided. The model is time dependent and uses factor vectors representing network parameters, load-related factors including transient event parameters, and external factors.
In step S20b, the actual hazard is modeled by applying the determined actual values (including at least the obtained values of the load-related factors, including the transient event parameters), the actual values of the network parameters and the actual values of the external factors of the factor vectors to the provided model.
In step S20c, risk factors are determined depending on the actual risk modeled.
While the invention has been described in terms of preferred embodiments, it will be apparent to those skilled in the art that modifications may be made in all embodiments.
Reference numbers:
10 distribution network
20 tubes
31. 32, 33 sensor
50 device
Multiple 51 sensors
52 determination unit
53 execution unit
Curve when C0 k is 0
Curve when C1 k is 1
Curve when C2 k is 2
Curve when C3 k is 3
d distance
k index
L1 measures position, location of first sensor
L2 measurement of position, positioning of second sensor
L3 measurement of position, location of third sensor
O output
First path of P1 pressure wave propagation
Second path of P2 pressure wave propagation
Third path for P3 pressure wave propagation
Method steps S10-S13
Method steps S20, S20a, S20b, S20c
Method steps S21-S23, S30
Curves V1, V2, V3, V4
Reference documents:
[1] large et al: "Decision support tools of Review of danger models in drinking water network asset management", journal of Water services, No. 10; 45-53,2015
[2] Sinha and Clair: "State-of-the-Technology Review on Water Pipe Condition, degradation and Failure Rate Prediction Models" can be found in RDDS
[3] "Application of Artificial Neural Networks (ANN) to model the failure of urban Water Main", mathematical and computer modeling, Vol 51, No 9-10, month 5 2010, Page 1170-1180
[4] Procedia engineering, volume 186, 2017, page 117-126.
Claims (15)
1. A method for operating a distribution network (10) having a particular network topology using N sensors (31-33) sensing wave front characteristics, each of the N sensors (31-33) being located at a particular measurement location (L1-L3) in the distribution network (10), the method comprising:
a) obtaining (S10) transient event parameter values for a particular transient event (E) in the distribution network (10) using at least a subset of the N sensors (31-33),
b) determining (S20) a risk factor indicative of a hazard in the distribution network (10) depending on the obtained transient event parameter value and an actual value of a network parameter indicative of the distribution network (10), and
c) performing (S30) one of a plurality of actions at the distribution network (10) depending on the determined risk factor.
2. The method according to claim 1, characterized in that the risk factor is determined in dependence of an actual value of the network parameter, an actual value of a load-related factor of a load distributed by the distribution network (10), and an external factor describing the environment of the distribution network (10), wherein the actual value of the load-related factor comprises the obtained transient event parameter value.
3. The method according to claim 1 or 2, characterized in that the transient event parameters comprise the amplitude of the specific transient event (E), the location of the specific transient event (E) in the distribution network (10) and/or the event type of the specific transient event (E) in the distribution network (10).
4. A method according to any one of claims 1 to 3, wherein step a) comprises: -using said at least a subset of said N sensors (31-33) to obtain said transient event parameter values for a plurality of specific transient events (E) in said distribution network (10).
5. The method according to any one of claims 1 to 4, wherein step a) (S10) comprises:
sensing (S11) wavefront characteristics caused by the particular transient event (E) in the distribution network (10) using the at least a subset of the N sensors (31-33),
collecting (S12) signals from the subset of the N sensors (31-33), the signals being indicative of sensed wavefront characteristics, an
Processing (S13) the collected signals to obtain the transient event parameters.
6. The method according to any one of claims 1 to 5, wherein step b) (S20) comprises:
providing (S20a) a model for modeling a hazard in the distribution network (10), the model being time-dependent and using factor vectors representing the network parameters, the load-related factors including the transient event parameters and the external factors,
modeling an actual hazard by applying to the provided model at least the determined actual values of the obtained load-related factor values comprising the transient event parameter, the actual values of the network parameters and the actual values of the external factors of the factor vectors (S20b), and
determining (S20c) the risk factor depending on the modeled actual risk.
7. The method of claim 6, wherein step b) comprises:
dividing the distribution network (10) into N interconnected pipe segmentsWhereinTo be provided withTo specify the ith tube segment and,
wherein the tube sections are separated from each other and each of the tube sections is homogenous at least in tube material and tube diameter.
8. The method of claim 7, wherein the formula
Is used for aligning the pipe sectionAssociated time-dependent real hazardsThe modeling is carried out so that,
10. The method according to claim 8, characterized in that the model for modeling the actual hazard uses a logistic regression model, wherein in the logistic regression model, a formula is used
11. The method according to any one of claims 8 to 10, characterized in that the coefficient vector β is learned based on historical data.
12. The method according to any one of claims 6 to 11, characterized in that a model is adapted to model reflections of the transient event (E) in the distribution network (10).
13. The method according to any of claims 6 to 12, wherein the factor vector comprises factors relating to different types of pressure transients.
14. An apparatus (50) for operating a distribution network (10) having a specific network topology, the apparatus (50) comprising:
a plurality (51) of N sensors (31-33) for sensing wave front characteristics, each of the N sensors (31-33) being located at a specific measurement location (L1-L3) in the distribution network (10), wherein at least a subset of the N sensors (31-33) is configured to obtain transient event parameter values for a specific transient event (E) in the distribution network (10),
a determining unit (52) for determining a risk factor indicative of a hazard in the distribution network (10) depending on the obtained transient event parameter value and an actual value of a network parameter indicative of the distribution network (10), and
an execution unit (53) for executing one of a plurality of actions at the distribution network (10) depending on the determined risk factor.
15. A distribution network (10) comprising a plurality of pipe segments for distributing a specific load and a device (50) according to claim 14 for operating the distribution network (10).
Applications Claiming Priority (3)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
RU2019000154 | 2019-03-12 | ||
RUPCT/RU2019/000154 | 2019-03-12 | ||
PCT/RU2019/000304 WO2020185113A1 (en) | 2019-03-12 | 2019-04-30 | Method and device for operating a distribution network |
Publications (1)
Publication Number | Publication Date |
---|---|
CN113906280A true CN113906280A (en) | 2022-01-07 |
Family
ID=72426770
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201980095885.9A Pending CN113906280A (en) | 2019-03-12 | 2019-04-30 | Method and apparatus for operating a distribution network |
Country Status (3)
Country | Link |
---|---|
EP (1) | EP3942271A1 (en) |
CN (1) | CN113906280A (en) |
WO (1) | WO2020185113A1 (en) |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112101811A (en) * | 2020-09-23 | 2020-12-18 | 正元地理信息集团股份有限公司 | Water supply network pipe explosion risk prediction method and system |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106471193A (en) * | 2014-07-03 | 2017-03-01 | 卡姆鲁普股份有限公司 | Pressure sensor apparatus for common network |
US20170076563A1 (en) * | 2015-09-15 | 2017-03-16 | General Electric Company | Systems and methods to provide pipeline damage alerts |
CN107013812A (en) * | 2017-05-05 | 2017-08-04 | 西安科技大学 | A kind of THM coupling line leakage method |
WO2018052675A1 (en) * | 2016-09-19 | 2018-03-22 | Exxonmobil Research And Engineering Company | A method and apparatus for real time enhancing of the operation of a fluid transport pipeline |
WO2018060340A1 (en) * | 2016-09-30 | 2018-04-05 | Telefonaktiebolaget Lm Ericsson (Publ) | Random access method for multiple numerology operation |
US20180292290A1 (en) * | 2015-10-09 | 2018-10-11 | Imperial Innovations Limited | Monitoring fluid dynamics |
-
2019
- 2019-04-30 CN CN201980095885.9A patent/CN113906280A/en active Pending
- 2019-04-30 EP EP19736832.7A patent/EP3942271A1/en active Pending
- 2019-04-30 WO PCT/RU2019/000304 patent/WO2020185113A1/en unknown
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106471193A (en) * | 2014-07-03 | 2017-03-01 | 卡姆鲁普股份有限公司 | Pressure sensor apparatus for common network |
US20170076563A1 (en) * | 2015-09-15 | 2017-03-16 | General Electric Company | Systems and methods to provide pipeline damage alerts |
US20180292290A1 (en) * | 2015-10-09 | 2018-10-11 | Imperial Innovations Limited | Monitoring fluid dynamics |
WO2018052675A1 (en) * | 2016-09-19 | 2018-03-22 | Exxonmobil Research And Engineering Company | A method and apparatus for real time enhancing of the operation of a fluid transport pipeline |
WO2018060340A1 (en) * | 2016-09-30 | 2018-04-05 | Telefonaktiebolaget Lm Ericsson (Publ) | Random access method for multiple numerology operation |
CN107013812A (en) * | 2017-05-05 | 2017-08-04 | 西安科技大学 | A kind of THM coupling line leakage method |
Non-Patent Citations (4)
Title |
---|
A . DEBON ET. AL.: ""Comparing risk of failure models in water supply network s using ROC curves"", RELIABILITY ENGINEERING AND SYSTEM SAFETY, vol. 95, no. 1, 5 August 2009 (2009-08-05), pages 43 - 48 * |
PENG LIN ET. AL.: ""Data Driven Water Pipe Failure Prediction: A Bayesian Nonparametric Approach"", CIKM \'15: PROCEEDINGS OF THE 24TH ACM INTERNATIONAL ON CONFERENCE ON INFORMATION AND KNOWLEDGE MANAGEMENT, 17 October 2015 (2015-10-17), pages 193 - 202, XP058998122, DOI: 10.1145/2806416.2806509 * |
SYMEON E. CHRISTODOULOU: ""Water Network Assessment and Reliability Analysis by Use of Survival Analysis"", WATER RESOUR MANAGE, vol. 25, no. 4, 19 June 2010 (2010-06-19), pages 1229 - 1238 * |
朱晓红;朱丹;: "支撑向量机在给水管网故障诊断中的应用", 重庆大学学报, no. 02, 15 February 2008 (2008-02-15), pages 179 - 182 * |
Also Published As
Publication number | Publication date |
---|---|
EP3942271A1 (en) | 2022-01-26 |
WO2020185113A1 (en) | 2020-09-17 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Tabesh et al. | Assessing pipe failure rate and mechanical reliability of water distribution networks using data-driven modeling | |
EP3671201B1 (en) | An improved method for evaluating pipe condition | |
US10242414B2 (en) | Method for locating a leak in a fluid network | |
Aksela et al. | Leakage detection in a real distribution network using a SOM | |
Laucelli et al. | Detecting anomalies in water distribution networks using EPR modelling paradigm | |
Amaya-Gómez et al. | Modeling of pipeline corrosion degradation mechanism with a Lévy Process based on ILI (In-Line) inspections | |
KR20140145637A (en) | System and method for monitoring resources in a water utility network | |
Moser et al. | Performance comparison of reduced models for leak detection in water distribution networks | |
El-Abbasy et al. | Unpiggable oil and gas pipeline condition forecasting models | |
US20230204166A1 (en) | Observation system, location and identification of damage in pipelines | |
CN113348349A (en) | Method and system for analyzing pipe condition | |
Amaya-Gómez et al. | A condition-based dynamic segmentation of large systems using a Changepoints algorithm: A corroding pipeline case | |
Berardi et al. | Active leakage control with WDNetXL | |
JP2022552498A (en) | Leak detection method | |
EP3857175B1 (en) | Detecting and quantifying liquid pools in hydrocarbon fluid pipelines | |
CN113906280A (en) | Method and apparatus for operating a distribution network | |
Okeya et al. | Locating pipe bursts in a district metered area via online hydraulic modelling | |
WO2014142825A1 (en) | Virtual in-line inspection of wall loss due to corrosion in a pipeline | |
WO2021034901A1 (en) | Localized metal loss estimation across piping structure | |
CN113063100A (en) | Pipeline leakage detection method and device | |
Boatwright et al. | Optimal sensor placement and leak/burst localisation in a water distribution system using spatially-constrained inverse-distance weighted interpolation | |
Jung | Robust and resilient water distribution systems | |
Shravani et al. | Cloud-based water leakage detection and localization | |
Smith et al. | Corrosion growth and remnant life assessment: How to pick the right approach for your pipeline | |
Kim | Adaptive Metaheuristic Scheme for Generalized Multiple Abnormality Detection in a Reservoir Pipeline Valve System |
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 |