CN116362720A - Leakage detection method, device and system for coping with operation change situation of water supply network - Google Patents
Leakage detection method, device and system for coping with operation change situation of water supply network Download PDFInfo
- Publication number
- CN116362720A CN116362720A CN202310333858.9A CN202310333858A CN116362720A CN 116362720 A CN116362720 A CN 116362720A CN 202310333858 A CN202310333858 A CN 202310333858A CN 116362720 A CN116362720 A CN 116362720A
- Authority
- CN
- China
- Prior art keywords
- water
- data
- water supply
- flow
- 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
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 title claims abstract description 216
- 238000001514 detection method Methods 0.000 title claims abstract description 41
- 230000008859 change Effects 0.000 title claims abstract description 24
- 230000010485 coping Effects 0.000 title claims description 11
- 238000000034 method Methods 0.000 claims abstract description 55
- 238000005259 measurement Methods 0.000 claims abstract description 51
- 238000001914 filtration Methods 0.000 claims abstract description 20
- 239000011159 matrix material Substances 0.000 claims description 34
- 238000004458 analytical method Methods 0.000 claims description 29
- 238000007405 data analysis Methods 0.000 claims description 17
- 238000012545 processing Methods 0.000 claims description 12
- 238000004364 calculation method Methods 0.000 claims description 10
- 238000007476 Maximum Likelihood Methods 0.000 claims description 6
- 238000012423 maintenance Methods 0.000 claims description 6
- 230000008569 process Effects 0.000 claims description 6
- 238000005070 sampling Methods 0.000 claims description 6
- 238000004891 communication Methods 0.000 claims description 4
- 238000004088 simulation Methods 0.000 claims description 4
- 230000002159 abnormal effect Effects 0.000 claims description 3
- 230000000295 complement effect Effects 0.000 claims description 3
- 238000012417 linear regression Methods 0.000 claims description 3
- 238000012544 monitoring process Methods 0.000 claims description 3
- 230000000644 propagated effect Effects 0.000 claims description 3
- 230000009466 transformation Effects 0.000 claims description 3
- 239000013598 vector Substances 0.000 claims description 3
- 238000010586 diagram Methods 0.000 description 6
- 230000006870 function Effects 0.000 description 6
- 238000010276 construction Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 229910001018 Cast iron Inorganic materials 0.000 description 1
- 229910001141 Ductile iron Inorganic materials 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000012886 linear function Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 230000001131 transforming effect Effects 0.000 description 1
Images
Classifications
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F17—STORING OR DISTRIBUTING GASES OR LIQUIDS
- F17D—PIPE-LINE SYSTEMS; PIPE-LINES
- F17D5/00—Protection or supervision of installations
- F17D5/02—Preventing, monitoring, or locating loss
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
-
- 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
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- 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
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06315—Needs-based resource requirements planning or analysis
-
- 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
- G06Q10/20—Administration of product repair or maintenance
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2113/00—Details relating to the application field
- G06F2113/08—Fluids
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2113/00—Details relating to the application field
- G06F2113/14—Pipes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/14—Force analysis or force optimisation, e.g. static or dynamic forces
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Tourism & Hospitality (AREA)
- Quality & Reliability (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Computational Mathematics (AREA)
- Game Theory and Decision Science (AREA)
- Mathematical Physics (AREA)
- Health & Medical Sciences (AREA)
- Pure & Applied Mathematics (AREA)
- Mathematical Optimization (AREA)
- Mathematical Analysis (AREA)
- Development Economics (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Health & Medical Sciences (AREA)
- Geometry (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Computer Hardware Design (AREA)
- Primary Health Care (AREA)
- Mechanical Engineering (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Water Supply & Treatment (AREA)
- Probability & Statistics with Applications (AREA)
- Public Health (AREA)
- Algebra (AREA)
- Educational Administration (AREA)
- Databases & Information Systems (AREA)
Abstract
The invention discloses a leakage detection method for a situation of operation change of a water supply network, which comprises the following steps: acquiring water supply network data to establish a hydraulic model, and acquiring inflow and outflow of the boundary of an independent metering area; establishing a water demand prediction model according to the acquired flow information, and establishing a water demand measurement model according to the historical flow information; the water demand prediction model and the water demand measurement model are combined, the water demand is corrected by using a nonlinear filtering method, and the corrected demand is placed into a hydraulic model of the water supply network to obtain the flow hydraulic state of the water supply network; and (3) calculating residual errors between the state output by the model and the actual measurement state, and analyzing whether leakage exists in the pipe network by utilizing the residual errors. The invention also provides a leakage detection device and a system for the situation of the operation change of the water supply network. The invention improves the alarm precision and the alarm efficiency, reduces the labor cost and helps the staff to find and overhaul in time.
Description
Technical Field
The invention belongs to the field of municipal engineering and urban water supply networks, and particularly relates to a leakage detection method, device and system for a situation of coping with operation change of a water supply network.
Background
The water supply network leakage not only wastes precious water resources, but also is inconsistent with the national policy call, and meanwhile, as the network leakage is self-negative of the water service company, the public water supply network leakage rate is too high, so that the great loss can be caused, the cost of the water supply enterprise is increased, and the cost pressure brought by the water service enterprise is increased. In addition, the water quality can be influenced by the leakage of the water supply network, and risks are brought to the water use safety of residents. In recent years, with the continuous promotion of urban construction in China, the construction of water supply network infrastructure related to national folk life becomes an insurmountable key point, and the reduction of water supply network leakage and the improvement of network management capability are the trends of promoting the development of intelligent water service industry.
The existing water supply network leakage detection method is a mature equipment method, the method is based on various detection instruments to detect the leakage of the network, the detection result is very dependent on manual experience, and the method is time-consuming and labor-consuming for detecting the leakage of the large-scale network. With the development of sensors and artificial intelligence, a data driving method has been developed, for example, chinese patent No. CN202211300518.8 discloses a method for detecting leakage of a water supply pipeline based on a neural network, and chinese patent No. CN202110707699.5 discloses a method and a system for detecting leakage of a water supply pipeline based on a long and short memory network model. However, these methods require a large amount of hydraulic data to train the proposed model, and are all methods for judging the occurrence of leakage by predicting that the residual magnitude between the flow or pressure of the pipe network under normal operation and actual measurement exceeds a certain threshold. In practice, once the water supply pipe network is manually operated (for example, a water pump in the pipe network is turned on), the change of the flow rate and the node pressure of the pipe network can be influenced, if the method is used, serious false alarm can be generated, unnecessary trouble is brought to leakage maintenance personnel, and the water consumption of residents is influenced.
Disclosure of Invention
In order to solve the technical problems in the prior art, the invention provides a leakage detection method, a leakage detection device and a leakage detection system for a situation of changing the operation of a water supply network, so that the problem that the leakage detection can still be carried out on the water supply network under the condition of manually adjusting the water supply network is solved, and unnecessary false alarm is avoided.
The leakage detection method for the water supply network operation change situation is characterized by comprising the following specific steps:
s1, acquiring water supply network data to establish a hydraulic model, and acquiring inflow and outflow of the boundary of an independent metering area;
s2, establishing a water demand prediction model according to the acquired flow information and establishing a water demand measurement model according to the historical flow information;
s3, the water demand prediction model and the water demand measurement model are combined, the water demand is corrected by using a nonlinear filtering method, and the corrected demand is placed into a hydraulic model of the water supply network to obtain the flow hydraulic state of the water supply network;
s4, analyzing whether leakage exists in the pipe network by utilizing residual errors between the state output by the calculation model and the actual measurement state.
Further, S1, acquiring water supply network data to establish a hydraulic model, and acquiring inflow and outflow of the boundary of an independent metering area, wherein the method specifically comprises the following steps:
acquiring data of a water supply network, including geographical information of the network, length of the pipeline and the like in reality, and modeling the data in hydraulic model simulation software according to the data;
dividing the whole urban pipe network into a plurality of independent metering areas, installing the flow meters of the Internet of things in the inlet and outlet pipes of each area, and counting the number NI of the flow meters of the water inlet pipe and the number NO of the flow meters of the water outlet pipe of each independent metering area.
Further, S2, a water demand prediction model is built according to the acquired flow information, and a water demand measurement model is built according to the historical flow information, specifically comprising:
the water demand at time t is recorded as d t The processing mode of the missing value and the abnormal value in the data is to carry out the complement and the replacement by adopting the average value of two adjacent acquisition time points; the water demand prediction model is established based on a multiple linear regression method according to the acquired historical monitoring data as follows:
wherein d t-1 、d t-2 、Respectively t-1 time, t-2 time and +.>Water demand at time; w (w) t-1 、w t-2 、/>The weight coefficients of the water demand quantity at corresponding moments are respectively, T is the sampling period of the flowmeter, the value of w is determined by maximum likelihood estimation, and the maximum likelihood function is as follows:
wherein W is W t-1 、w t-2 、The column vectors, sigma is the standard deviation to be estimated, N represents the number of historical data, +.>Is the ith real demand data before the time t, W T d i Representing the water demand calculated by the predictive model;
also, historical flow information may be used to build a water demand measurement model:
z t =h(x t ,u t )+v t ,v t ~N[0,R t ]
where h is the estimated x with respect to a priori water demand t And water supply network operation information u t Is a nonlinear function of (2); v t Is measurement noise obeying normal distribution, and the covariance matrix is R t ;
Further, S3, combining a water demand prediction model and a water demand measurement model, correcting the water demand by using a nonlinear filtering method, and placing the corrected demand into hydraulic model software of the water supply network to simulate to obtain the flow hydraulic state of the water supply network, wherein the method specifically comprises the following steps:
the joint equations of the state equation and the measurement equation of the system are as follows:
the first equation in the joint equations is recorded as a state equation, and the second equation is recorded as a measurement equation; wherein w is t 、v t Respectively process noise and measurement noise obeying normal distribution, and the corresponding covariance matrixes are respectively Q t 、R t H is an estimate x of a priori water demand t And water supply network operation information u t Is a nonlinear function of (2);
the method for correcting the water demand by using nonlinear filtering specifically comprises the following steps:
s31, respectively recording the estimated value of the water demand at the time t-1 and the corresponding covariance asP t-1|t-1 For the given +.>P t-1|t-1 Solving for the state one-step prediction +.>Covariance matrix P of prediction error t|t-1 :
S311, calculating a set of sampling points, which are marked as sigma points, based on the obtained estimated water demand data
Wherein, the weight distribution parameters of the sigma point are as follows:
where n represents the dimension of the estimator, λ is a constant, and can be expressed generally as λ=α 2 (n+k) -n, k is greater than or equal to 0, and generally k takes the value of 0; a epsilon (0, 1)]A is mainly used for adjusting the influence of a higher-order term on a model, and generally takes the value of a=0.01; beta is used to describe x t The value of the distribution information of (2) is near 2;representation matrix (n+lambda) P t-1∣t-1 Is the ith column of the square root matrix; />Weight coefficients for first-order statistical characteristics; />Weight coefficients for the second-order statistical characteristics;
wherein f t The model is a generalized state equation, and is a water demand prediction model at the moment t;is one-step predictive, P t∣t-1 Is a state prediction error covariance matrix, Q t-1 Is a process noise covariance matrix at the time t-1;
s32, adopting unscented transformation to solve the propagation of the sigma point through a measurement equation;
S322, one-step advanced prediction of the calculated output, i.e
Wherein,,is one-step advance prediction of the output of the time t and sigma points, h t Is a nonlinear function, here a model of water demand measurement at time t +>Is a one-step advance prediction of the state at time t,/-, for example>Represents the covariance matrix of the measurement error,to measure the covariance matrix of the prediction error, R t Measuring covariance matrix at t moment;
s33, obtaining a new measurement z t Then calculate Kalman gain K t And updating state variablesAnd its corresponding covariance P t|t And (5) performing filtering update:
calculating an updated state from step S33After the corresponding covariance, substituting the value into S31, performing iterative computation for multiple times to obtain an accurate water demand prediction result, and placing the corrected demand into hydraulic model software of the water supply network to simulate to obtain the flow hydraulic state of the water supply network
Further, S4, analyzing whether the pipe network has leakage or not by calculating residual errors between the state output by the model and the actual measurement state, wherein the method specifically comprises the following steps:
firstly, according to the flow hydraulic state of the water supply network calculated in the step S33Calculating flow residual +.>I.e. calculating the flow value obtained by simulation prediction +.>Flow value +.>Difference between->Normalize the residual to +.>
Secondly, the normalized residual is dimensionless:
nQ (i,j) the method comprises the steps that at the moment i, standardized flow residual errors of j nodes are represented, tot is the total node number in a pipe network, and m is the number of the standardized flow residual errors;
and finally, calculating the average value of the dimensionless standardized residual errors under the normal working condition of the water supply network, comparing the dimensionless standardized residual errors at the current moment, and if the average value of the dimensionless standardized residual errors calculated in the last step is larger than the average value of the dimensionless standardized residual errors, leaking.
Further, in order to detect an emergency, an adjustment factor is added after the nonlinear filter method in step 3, so as to correct the kalman gain, which is specifically as follows:
kalman gain K t Weight coefficients based on prior and observed error covariance matrices:
wherein P is t Is the error covariance matrix at the moment t;
to cope with the emergency, the nonlinear filter is modified here, and an adjustment factor is added, and the modified kalman gain can be written as:
wherein a is t The adjustment matrix is adjusted, and the adjustment coefficient is the ratio of the observed flow of the current time step to the corrected flow of the previous time step; the calculation formula of the ratio is:
wherein,,a i,t and->Respectively an adjustment coefficient and a second adjustment coefficient of the i-number flowmeter in the time step t; />And->The corrected flow of the i-meter at the previous time step and the observed flow of the current time step t are respectively.
Leakage detection device under reply water supply network operation change sight, characterized in that includes:
the pipe network data acquisition module is used for acquiring basic data information of all pipe networks in the area and comprises water pressure data, water level data and water flow data of each node unit river basin in the current acquisition area;
the pipe network leakage analysis processing module is used for predicting the water demand based on the water demand prediction model, correcting the demand and analyzing the pipe network leakage by a nonlinear filtering method so as to obtain a leakage detection analysis result in the acquisition area;
and the pipe network early warning module is used for confirming the leakage detection analysis result obtained by the pipe network leakage analysis processing module to be in a leakage state, generating early warning information comprising leakage point pipeline data, water flow data, water pressure data and position data, and sending the early warning information to early warning equipment so that the early warning equipment informs relevant maintenance personnel according to the early warning information.
The leakage detection system for the situation of the operation change of the water supply network is characterized by comprising network data acquisition equipment, network data analysis equipment, network alarm equipment and terminal equipment, wherein the network data acquisition equipment, the network alarm equipment and the terminal equipment are connected with the network data analysis equipment through communication equipment;
the pipe network data acquisition equipment is used for acquiring water pressure data, water level data and water flow data of each node unit basin in the area;
the pipe network data analysis equipment is used for acquiring data sent by the pipe network data acquisition equipment, estimating water demand based on a nonlinear filtering method, and performing leakage analysis so as to obtain a leakage detection result in a corresponding area;
the pipe network alarm equipment is used for generating alarm information including leakage point pipeline data, water flow data, water pressure data and position data if the leakage detection analysis result obtained by the pipe network data analysis equipment is a leakage state, and sending the alarm information to the early warning equipment so that the early warning equipment informs related maintenance personnel according to the early warning information;
the terminal equipment is used for receiving the analysis data and the pipeline leakage analysis result sent by the pipe network data analysis equipment and visualizing the analysis data and the pipeline leakage analysis result;
the pipe network data analysis device is used for executing the leakage detection method for the situation of coping with the operation change of the water supply pipe network according to the claims 1-6.
Compared with the prior art, the invention has the beneficial effects that:
1. the invention considers the operation of the water supply network with artificial factors, starts from the forecast water demand, and avoids the prior art from generating a large number of false alarms under the same condition.
2. The nonlinear filtering method only uses a small amount of calibration data, reduces the calculation time, can detect the pipeline leakage in a near real-time mode, and helps workers find and overhaul in time.
3. According to the invention, the data acquisition equipment is used for acquiring the pipe network related data, the data analysis is used for analyzing and processing the pipe network related data acquired by the data acquisition equipment, and the detection result of the pipe network leakage of the target area is determined, so that the alarm information is generated, and then the alarm equipment is used for alarming.
Drawings
Fig. 1 is a flowchart of a leakage detection method in a situation of coping with an operation change of a water supply network according to a first embodiment of the present invention;
FIG. 2 is a schematic diagram of a water supply network model and a pressure sensor in city A according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of simulation of pipeline leakage detection in accordance with an embodiment of the present invention;
FIG. 4 is a flow chart of a leakage detection method in a situation of coping with operation change of a water supply network according to a second embodiment of the present invention;
fig. 5 is a schematic structural diagram of a leakage detection device in a situation of coping with operation change of a water supply network according to a third embodiment of the present invention;
fig. 6 is a schematic diagram of a leak detection system in a situation of coping with an operation change of a water supply network according to a fourth embodiment of the present invention.
Detailed Description
In order to make the technical scheme of the present invention clearer, the technical scheme provided by the present invention will be described in detail below with reference to specific embodiments, and the present invention will be further described with reference to the accompanying drawings. It will be apparent that the described embodiments are only some, but not all, embodiments of the invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Example 1
Fig. 1 is a flowchart of a method for detecting leakage in a situation of operation change of a water supply network according to an embodiment of the present invention, where the method may be implemented by a device or a system for detecting and predicting leakage in a situation of operation change of a water supply network, and the device may be implemented by software and hardware, as shown in fig. 1, and the method specifically includes the following steps:
step 1: and acquiring water supply network data to establish a hydraulic model, and acquiring inflow and outflow of the boundary of the independent metering area.
Specifically, basic data of a water supply network is firstly obtained through a geographic information system and a water service company, for example, the city A consists of 305 nodes, 238 pipelines and 87 valves, and water is supplied to about 12000 people. Modeling is performed in the hydraulic model analysis software based on these data. And then dividing and installing a meter for the water supply network in the city A, dividing the water supply network into 5 independent metering areas which are respectively an area 1, an area 2, an area … and an area 5, and installing a flowmeter of the Internet of things in an inlet and outlet pipeline of each area, as shown in figure 2.
And secondly, counting the flow of the boundary pipe network, and counting the number NI of the water inlet pipeline flow meters and the number NO of the water outlet pipeline flow meters in each independent metering area, wherein as shown in a table 1, the table 1 is an inlet and outlet flow meter number meter in the independent metering area of the water supply pipe network in the city A.
Table 1A number of inlet and outlet flow meters in independent metering areas of municipal water supply network
And finally, collecting the inlet flow data and the outlet flow data of each area at the time t by a data remote communication mode. Taking inlet and outlet flow data of 12:00 of region 1 in 2022, 8 months, 1 days in water supply pipe network of city a as an example, each inlet and outlet flow data is shown in table 2.
Table 2 area 1 ingress and egress flow data
Step 2: and establishing a water demand prediction model and historical flow information according to the acquired flow information to establish a water demand measurement model.
2.1 acquiring inlet time sequence flow data of the boundaries of the region 1, the region 2, the region … and the region 5 respectively by using a flowmeter, wherein the water demand at the moment t is recorded as d t . The processing mode of the missing value and the abnormal value in the data is to carry out the complement and the replacement by adopting the average value of two adjacent acquisition time points. The water demand prediction model is established based on a multiple linear regression method according to the acquired historical demand data, and is as follows:
wherein d t-1 、d t-2 、Respectively t-1 time, t-2 time and +.>Water demand at time. w (w) t-1 、w t-2 、/>The weight coefficients of the water demand quantity at corresponding moments are respectively, T is the sampling period of the flowmeter, the value of w is determined by maximum likelihood estimation, and the maximum likelihood function is that
Wherein W is W t-1 、w t-2 、The column vectors, sigma is the standard deviation to be estimated, N represents the number of historical data, +.>The ith real demand data, W, is before the time t T d i Representing the demand calculated by the predictive model. Thereby calculating the water demand d at the time t t 。
2.2 using the historical flow information to build a water demand measurement model.
The water demand measurement model for the individual metering areas is calibrated offline using water demand and pressure data over a cycle time. The independent metering zone has a pressure sensor located at the highest elevation point of the independent metering zone. The roughness and basic requirements of all plastic pipes remain unchanged. The calibration parameters of the hydraulic model (adjusted by adopting the trial-and-error technology) are as follows: 1) Roughness values of cast iron pipes and ductile iron pipes; 2) The relative opening of the throttle control valve at the inlet of the independent metering area is gradually increased; 3) The demand factor is modified every 15 minutes so that the predicted flow rate coincides with the inlet and outlet flow rates in real life. All of these modifications are to ensure that the predicted pressure head pattern is closely related to the observed pressure head pattern.
Thus, historical flow information may be used to build a water demand measurement model:
z t =h(x t ,u t )+v t ,v t ~N[0,R t ](3)
where h is the estimated x with respect to a priori water demand t And water supply network operation information u t Is a non-linear function of (2). v t Is measurement noise obeying normal distribution, and the covariance matrix is R t 。
Step 3: and the water demand prediction model and the water demand measurement model are combined, and the water demand is corrected by using a nonlinear filtering method.
Preferably, the joint equations of the water demand prediction model and the water demand measurement model of the system are as follows:
the first equation of the above joint equations is recorded as a state equation, and the second equation is a measurement equation. Wherein w is t Is the process noise obeying normal distribution, and the corresponding covariance matrix is Q t 。
Preferably, the method for correcting the water demand by using nonlinear filtering specifically comprises:
3.1 recording the estimated value of the water demand at time t-1 and the corresponding covariance asP t-1|t-1 For the given +.>P t-1|t-1 Solving for the state one-step prediction +.>Covariance matrix P of prediction error t|t-1 :
1) Calculating a set of sampling points, designated as sigma points, from the obtained estimated water demand data, i.e
The weight distribution parameters of the sigma point are as follows:
where n represents the dimension of the estimator, λ is a constant, and can be expressed generally as λ=α 2 (n+k) -n, k is greater than or equal to 0, and generally k takes the value of 0; alpha epsilon (0, 1)]Alpha is mainly used for adjusting the influence of a higher order term on a model, and the value alpha=0.01 is generally adopted; beta is used to describe x t The value of the distribution information of (2) is near 2;representation matrix (n+lambda) P t-1∣t-1 Is the ith column of the square root matrix; />Weight coefficients for first-order statistical characteristics; />For the weight coefficient in the second-order statistical characteristic.
wherein f t The model is a generalized state equation, and is a water demand prediction model at the moment t;is one-step predictive, P t∣t-1 Is a state prediction error covariance matrix, Q t-1 Is the process noise covariance matrix at time t-1.
3.2, adopting unscented transformation to calculate the propagation of sigma point through the measurement equation, namely:
2) One-step advance prediction of computational output, i.e.
Wherein,,is one-step advance prediction of the output of the time t and sigma points, h t Is a nonlinear function, here a model of water demand measurement at time t +>Is a one-step advance prediction of the state at time t,/-, for example>Represents the covariance matrix of the measurement error,to measure the covariance matrix of the prediction error, R t Is the measurement covariance matrix at time t.
3.3 obtaining a new measurement z t Then calculate Kalman gain K t And updating state variablesAnd its corresponding covariance P t|t And (5) performing filtering update: />
The steps are iterated a plurality of times, so that an accurate water demand prediction result can be obtained. The corrected demand is put into hydraulic model software of the water supply network to simulate and obtain the flow hydraulic state of the water supply network
Step 4: and calculating residual errors between the state output by the model and the actual measurement state, and analyzing whether leakage exists in the pipe network by utilizing the residual errors.
Firstly, calculating the flow hydraulic state of the water supply network according to the step 3.3Calculating flow residual +.>I.e. calculating the flow value obtained by simulation prediction +.>Flow value +.>Difference between->Normalize the residual to +.>Secondly, dimensionless transforming the normalized residual error:
nQ (i,j) and (3) representing the standardized flow residual error of the j nodes at the moment i, wherein tot is the total node number in the pipe network, and m is the number of the standardized flow residual errors.
And finally, calculating the average value of the dimensionless standardized residual errors under the normal working condition of the water supply network, and comparing the dimensionless standardized residual errors at the current moment, wherein if the average value of the dimensionless standardized residual errors calculated in the last step is larger than the average value of the dimensionless standardized residual errors, leakage exists, as shown in fig. 3.
The accuracy of leakage detection is 85.61% obtained through calculation under the condition of water supply network operation change, and the method using nonlinear filtering in the embodiment only uses a small amount of calibration data, so that the calculation time is reduced, the pipeline leakage can be detected in a near real-time mode, and workers can find and overhaul the pipeline in time.
Example two
Fig. 4 is a flowchart of a leak detection method in a situation of coping with an operation change of a water supply network according to a second embodiment of the present invention. The technical scheme of the embodiment adds new steps on the basis of the embodiment. Optionally, to detect an emergency event, the nonlinear filter is used to correct the kalman gain by adding an adjustment factor. For a part of this method embodiment which is not described in detail, reference is made to the first embodiment described above. Referring specifically to fig. 3, the method may include the steps of:
step 1: inflow and outflow of the boundary of the independent metering region are obtained.
Step 2: and establishing a water demand prediction model and historical flow information according to the acquired flow information to establish a water demand measurement model.
Step 3: and the water demand prediction model and the water demand measurement model are combined, and the water demand is corrected by using a nonlinear filtering method.
Step 4: and adding an adjustment factor to correct the Kalman gain.
Kalman gain K t Weight coefficients based on prior and observed error covariance matrices:
wherein P is t Is the time t error covariance matrix.
To cope with the emergency, the nonlinear filter is modified here, and an adjustment factor is added, and the modified kalman gain can be written as:
wherein a is t Is an adjustment matrix, and the adjustment coefficient is the ratio of the observed flow of the current time step to the corrected flow of the previous time step. The calculation formula of the ratio is:
wherein the method comprises the steps ofa i,t And->Respectively an adjustment coefficient and a second adjustment coefficient of the i-number flowmeter in the time step t; />And->The corrected flow of the i-meter at the previous time step and the observed flow of the current time step t are respectively.
Step 5: and calculating residual errors between the state output by the model and the actual measurement state, and analyzing whether leakage exists in the pipe network by utilizing the residual errors.
Example III
Fig. 5 is a schematic structural diagram of a leakage detection device for a situation of changing operation of a water supply network according to a third embodiment of the present invention. The device is configured in a data analysis device. Referring to fig. 5, the apparatus includes: pipe network data acquisition module, pipe network leakage analysis processing module and pipe network early warning module:
the pipe network data acquisition module is used for acquiring basic data information of all pipe networks in the area, including water pressure data, water level data, water flow data and the like of each node unit river basin in the current acquisition area;
and the pipe network leakage analysis processing module is used for predicting the water demand based on the water demand prediction model, correcting the demand and analyzing the pipe network leakage by a nonlinear filtering method so as to obtain a leakage detection analysis result in the acquisition area.
And the pipe network early warning module is used for generating early warning information including leakage point pipeline data, water flow data, water pressure data and position data if the leakage detection analysis result obtained by the pipe network leakage analysis processing module is a leakage state, and sending the alarm information to early warning equipment so that the early warning equipment informs related maintenance personnel according to the early warning information.
On the basis of the technical schemes, the pipe network leakage analysis processing module is further used for carrying out pipe leakage analysis on the water flow evolution result based on the pipe network water demand model and the hydraulic model, and calculating the pipe leakage analysis result of the current monitoring area by adopting a nonlinear optimization method, wherein the pipe leakage analysis result at least comprises the water quantity, the flow rate, the water pressure and the position of the unit drainage basin of the current target area.
Example IV
Fig. 6 is a schematic diagram of a leakage detection system for a situation of operation change of a water supply network according to a fourth embodiment of the present invention, including: the system comprises data acquisition equipment, data analysis equipment, alarm equipment and terminal equipment;
the data acquisition equipment, the alarm equipment and the terminal equipment are connected with the data analysis equipment through the communication equipment; the data analysis device is used for executing the leakage detection method for the situation of coping with the operation change of the water supply network according to the claims 1-6.
And the data acquisition equipment is provided with a meter at the dividing part of the pipe network, and an Internet of things flowmeter is arranged at the inlet and outlet pipelines of each area. Collecting water pressure data, water level data, water flow data and the like of each node unit river basin in the area;
the data analysis device is used for acquiring data sent by the data acquisition device, estimating water demand based on a nonlinear filtering method, and performing leakage analysis so as to obtain a leakage detection result in a corresponding area.
And the alarm equipment is used for generating alarm information including leakage point pipeline data, water flow data, water pressure data and position data if the leakage detection analysis result obtained by the data analysis equipment is a leakage state, and sending the alarm information to the early warning equipment so that the early warning equipment informs related maintenance personnel according to the early warning information.
The terminal equipment is used for receiving the analysis data and the pipeline leakage analysis result sent by the data analysis equipment and visualizing the analysis data and the pipeline leakage analysis result.
The embodiments described in this specification are merely illustrative of the manner in which the inventive concepts may be implemented. The scope of the present invention should not be construed as being limited to the specific forms set forth in the embodiments, but the scope of the present invention and the equivalents thereof as would occur to one skilled in the art based on the inventive concept.
Claims (8)
1. The leakage detection method for the water supply network operation change situation is characterized by comprising the following specific steps:
s1, acquiring water supply network data to establish a hydraulic model, and acquiring inflow and outflow of the boundary of an independent metering area;
s2, establishing a water demand prediction model according to the acquired flow information and establishing a water demand measurement model according to the historical flow information;
s3, the water demand prediction model and the water demand measurement model are combined, the water demand is corrected by using a nonlinear filtering method, and the corrected demand is placed into a hydraulic model of the water supply network to obtain the flow hydraulic state of the water supply network;
s4, analyzing whether leakage exists in the pipe network by utilizing residual errors between the state output by the calculation model and the actual measurement state.
2. A leakage detecting method according to claim 1, wherein,
s1, acquiring water supply network data to establish a hydraulic model, and acquiring inflow and outflow of an independent metering area boundary, wherein the method specifically comprises the following steps of:
acquiring data of a water supply network, including geographical information of the network, length of the pipeline and the like in reality, and modeling the data in hydraulic model simulation software according to the data;
dividing the whole urban pipe network into a plurality of independent metering areas, installing the flow meters of the Internet of things in the inlet and outlet pipes of each area, and counting the number NI of the flow meters of the water inlet pipe and the number NO of the flow meters of the water outlet pipe of each independent metering area.
3. A leakage detecting method according to claim 1, wherein,
s2, establishing a water demand prediction model according to the acquired flow information and establishing a water demand measurement model according to the historical flow information, wherein the method specifically comprises the following steps:
the water demand at time t is recorded as d t The processing mode of the missing value and the abnormal value in the data is to carry out the complement and the replacement by adopting the average value of two adjacent acquisition time points; the water demand prediction model is established based on a multiple linear regression method according to the acquired historical monitoring data as follows:
wherein d t-1 、d t-2 、Respectively at time t-1 and time t-2Score and +.>Water demand at time; w (w) t-1 、w t-2 、/>The weight coefficients of the water demand quantity at corresponding moments are respectively, T is the sampling period of the flowmeter, the value of w is determined by maximum likelihood estimation, and the maximum likelihood function is as follows:
wherein W is W t-1 、w t-2 、The column vectors, sigma is the standard deviation to be estimated, N represents the number of historical data, +.>Is the ith real demand data before the time t, W T d i Representing the water demand calculated by the predictive model;
also, historical flow information may be used to build a water demand measurement model:
z t =h(x t ,u t )+v t ,v t ~N[0,R t ]
where h is the estimated x with respect to a priori water demand t And water supply network operation information u t Is a nonlinear function of (2); v t Is measurement noise obeying normal distribution, and the covariance matrix is R t ;
4. A leakage detecting method according to claim 1, wherein,
s3, combining the water demand prediction model and the water demand measurement model, correcting the water demand by using a nonlinear filtering method, and placing the corrected demand into hydraulic model software of the water supply network to simulate to obtain the flow hydraulic state of the water supply network, wherein the method specifically comprises the following steps of:
the joint equations of the state equation and the measurement equation of the system are as follows:
the first equation in the joint equations is recorded as a state equation, and the second equation is recorded as a measurement equation; wherein w is t 、v t Respectively process noise and measurement noise obeying normal distribution, and the corresponding covariance matrixes are respectively Q t 、R t H is an estimate x of a priori water demand t And water supply network operation information u t Is a nonlinear function of (2);
the method for correcting the water demand by using nonlinear filtering specifically comprises the following steps:
s31, respectively recording the estimated value of the water demand at the time t-1 and the corresponding covariance asP t-1|t-1 For the given +.>P t-1|t-1 Solving for the state one-step prediction +.>Covariance matrix P of prediction error t|t-1 :
S311, calculating a set of sampling points, which are marked as sigma points, based on the obtained estimated water demand data
Wherein, the weight distribution parameters of the sigma point are as follows:
where n represents the dimension of the estimator, λ is a constant, and can be expressed generally as λ=α 2 (n+k) -n, k is greater than or equal to 0, and generally k takes the value of 0; alpha epsilon (0, 1)]Alpha is mainly used for adjusting the influence of a higher order term on a model, and the value alpha=0.01 is generally adopted; beta is used to describe x t The value of the distribution information of (2) is near 2;representation matrix (n+lambda) P t-1∣t-1 Is the ith column of the square root matrix; />Weight coefficients for first-order statistical characteristics;
wherein f t The model is a generalized state equation, and is a water demand prediction model at the moment t;is one-step predictive, P t∣t-1 Is a state prediction error covariance matrix, Q t-1 Is a process noise covariance matrix at the time t-1;
s32, adopting unscented transformation to solve the propagation of the sigma point through a measurement equation;
S322, one-step advanced prediction of the calculated output, i.e
Wherein,,is one-step advance prediction of the output of the time t and tau point, h t Is a nonlinear function, here a model of water demand measurement at time t +>Is a one-step advance prediction of the state at time t,/-, for example>Indicating the measurement error covariance matrix +_>To measure the covariance matrix of the prediction error, R t Measuring covariance matrix at t moment;
S33,in obtaining new measurements z t Then calculate Kalman gain K t And updating state variablesAnd its corresponding covariance P t|t And (5) performing filtering update:
after the updated state and the corresponding covariance are calculated in the step S33, substituting the value into the step S31, performing repeated iterative computation to obtain an accurate water demand prediction result, and placing the corrected demand into hydraulic model software of the water supply network to simulate to obtain the flow hydraulic state of the water supply network
5. A leakage detecting method according to claim 1, wherein,
s4, analyzing whether leakage exists in the pipe network by utilizing residual errors between the state output by the calculation model and the actual measurement state, wherein the method specifically comprises the following steps:
firstly, according to the flow hydraulic state of the water supply network calculated in the step S33Calculating flow residual +.>I.e. calculating the flow value obtained by simulation prediction +.>Flow value +.>Difference between->Normalize the residual to +.>
Secondly, the normalized residual is dimensionless:
wherein nQ i Is the normalized flow residual at the moment i, nQ (i,j) the method comprises the steps that at the moment i, standardized flow residual errors of j nodes are represented, tot is the total node number in a pipe network, and m is the number of the standardized flow residual errors;
and finally, calculating the average value of the dimensionless standardized residual errors under the normal working condition of the water supply network, comparing the dimensionless standardized residual errors at the current moment, and if the average value of the dimensionless standardized residual errors calculated in the last step is larger than the average value of the dimensionless standardized residual errors, leaking.
6. A leakage detecting method according to claim 1, wherein,
in order to detect the emergency, an adjustment factor is added after the nonlinear filter method in the step 3, so as to correct the kalman gain, which is specifically as follows:
Ka Ermangan gain K t Weight coefficients based on prior and observed error covariance matrices:
wherein P is t Is the error covariance matrix at the moment t;
to cope with the emergency, the nonlinear filter is modified here, and an adjustment factor is added, and the modified kalman gain can be written as:
wherein a is t The adjustment matrix is adjusted, and the adjustment coefficient is the ratio of the observed flow of the current time step to the corrected flow of the previous time step; the calculation formula of the ratio is:
7. Leakage detection device under reply water supply network operation change sight, characterized in that includes:
the pipe network data acquisition module is used for acquiring basic data information of all pipe networks in the area and comprises water pressure data, water level data and water flow data of each node unit river basin in the current acquisition area;
the pipe network leakage analysis processing module is used for predicting the water demand based on the water demand prediction model, correcting the demand and analyzing the pipe network leakage by a nonlinear filtering method so as to obtain a leakage detection analysis result in the acquisition area;
and the pipe network early warning module is used for confirming the leakage detection analysis result obtained by the pipe network leakage analysis processing module to be in a leakage state, generating early warning information comprising leakage point pipeline data, water flow data, water pressure data and position data, and sending the early warning information to early warning equipment so that the early warning equipment informs relevant maintenance personnel according to the early warning information.
8. The leakage detection system for the situation of the operation change of the water supply network is characterized by comprising network data acquisition equipment, network data analysis equipment, network alarm equipment and terminal equipment, wherein the network data acquisition equipment, the network alarm equipment and the terminal equipment are connected with the network data analysis equipment through communication equipment; the pipe network data analysis device is used for executing the leakage detection method for the situation of coping with the operation change of the water supply pipe network according to the claims 1-6.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310333858.9A CN116362720A (en) | 2023-03-31 | 2023-03-31 | Leakage detection method, device and system for coping with operation change situation of water supply network |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310333858.9A CN116362720A (en) | 2023-03-31 | 2023-03-31 | Leakage detection method, device and system for coping with operation change situation of water supply network |
Publications (1)
Publication Number | Publication Date |
---|---|
CN116362720A true CN116362720A (en) | 2023-06-30 |
Family
ID=86930194
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202310333858.9A Pending CN116362720A (en) | 2023-03-31 | 2023-03-31 | Leakage detection method, device and system for coping with operation change situation of water supply network |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN116362720A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117150693A (en) * | 2023-09-03 | 2023-12-01 | 深圳市水务科技发展有限公司 | Drainage pipe network hybrid-joint transformation optimization model system based on deep learning |
CN117195778A (en) * | 2023-11-08 | 2023-12-08 | 天津市津安热电有限公司 | Parameter identification correction method for hydraulic simulation model of heating pipe network |
-
2023
- 2023-03-31 CN CN202310333858.9A patent/CN116362720A/en active Pending
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117150693A (en) * | 2023-09-03 | 2023-12-01 | 深圳市水务科技发展有限公司 | Drainage pipe network hybrid-joint transformation optimization model system based on deep learning |
CN117195778A (en) * | 2023-11-08 | 2023-12-08 | 天津市津安热电有限公司 | Parameter identification correction method for hydraulic simulation model of heating pipe network |
CN117195778B (en) * | 2023-11-08 | 2024-02-20 | 天津市津安热电有限公司 | Parameter identification correction method for hydraulic simulation model of heating pipe network |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN112182984B (en) | Real-time simulation method for sewage pipe network based on water supply Internet of things data driving | |
CN109376925A (en) | Water supply network node flow dynamic self-adapting optimization method | |
CN108197725B (en) | Water demand prior information-based water supply network node water demand checking method | |
WO2023284060A1 (en) | Geographic three-dimensional information-based method for analyzing uncertainty of flow rate of sewage pipe network | |
CN116362720A (en) | Leakage detection method, device and system for coping with operation change situation of water supply network | |
US20230205943A1 (en) | Real-time simulation method of sewage pipe network based on water supply iot data assimilation | |
CN111401529A (en) | River ecological flow supervision method based on remote sensing technology | |
CN108758357B (en) | A kind of localization of bursted pipe method based on the analysis of water supply network change value of pressure | |
CN113221439B (en) | BP neural network-based drainage system real-time calibration and dynamic prediction method | |
CN114048694B (en) | Leakage positioning method based on Internet of things and hydraulic model | |
CN112113146B (en) | Synchronous self-adaptive check method for roughness coefficient and node water demand of water supply pipe network pipeline | |
CN112836941A (en) | Online health condition evaluation method for high-pressure steam turbine system of coal-electric unit | |
CN112818495A (en) | Novel dynamic correction method for pipeline pressure drop measurement and calculation algorithm parameters | |
CN114936742A (en) | Water supply system scheduling agent decision method | |
CN117540329B (en) | Online early warning method and system for defects of drainage pipe network based on machine learning | |
CN113626959B (en) | Sewage pipe network hydraulic model building method based on three-dimensional geographic information | |
CN116823067B (en) | Method and device for determining water quality cleaning state of pipe network and electronic equipment | |
CN112780953B (en) | Independent metering area pipe network leakage detection method based on mode detection | |
CN117469603A (en) | Multi-water-plant water supply system pressure optimal control method based on big data learning | |
CN117073933A (en) | Pipeline pressure monitoring method and system for gas pipe network | |
CN116227322A (en) | Online self-adaption method for digital twin system model of nuclear power plant | |
CN114202450A (en) | High-precision intelligent flow monitoring sensor based on block chain | |
CN112097125B (en) | Water supply pipe network pipe burst detection and positioning method based on self-adaptive checking | |
Hu et al. | Supply pressure transfer modeling for water distribution network systems based on correlation analysis | |
CN116108685A (en) | Water supply pipe network pipe section state judging method based on flow and water loss relation |
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 |