Generating topology of water distribution network based on readings of water meters in the network

Abstract

A system (35) includes an interface (20) and a processor (22). The interface (20) is configured to receive multiple time sequences of readings acquired by multiple flow sensors (11, 12-16, 18, 19, 121-124, 131-133, 141, 142, 151, 152, 161) disposed at multiple respective locations within a distribution system (33) of a fluid, each of the readings being indicative of a flow of the fluid flowing through one of the flow sensors, and the processor (22) is configured to produce a topology of the distribution system based on: (i) one or more correlations between selected pairs of the time sequences, and (ii) one or more variances between chosen pairs of the time sequences.

Description

[0001] GENERATING TOPOLOGY OF WATER DISTRIBUTION NETWORK BASED ON READINGS OF WATER METERS IN THE NETWORK

[0002] CROSS-REFERENCE TO RELATED APPLICATIONS

[0003] This application claims the benefit of U.S. Provisional Patent Application 63 / 676,945, filed July 30, 2024, whose disclosure is incorporated herein by reference.

[0004] FIELD OF THE INVENTION

[0005] The present invention relates generally to mapping and controlling water distribution systems, and particularly to methods and systems for generating topology of a water distribution network based on readings of water meters in the network.

[0006] BACKGROUND OF THE INVENTION

[0007] Various techniques for modeling water distribution systems have been published.

[0008] For example, U.S. Patent Application Publication 2014 / 0052421, describes a method of modelling a water distribution system, the method comprising steps of identifying a plurality of demand zones within said water distribution network; estimating water consumption data for said demand zones; simulating the hydraulic characteristics of the water distribution system using said estimated water consumption data and so; providing simulated pressure and flow rates within said demand zones; receiving output from sensors within said water distribution network in the form of pressure and flow rate data; correcting the simulated pressure and flow rate data within said demand zones based upon the sensor output and so; calibrating a model of the water distribution system.

[0009] PCT International Publication WO 2013 / 121298 describes a system and a method for analyzing geographical information system (GIS) data to improve operation and monitoring of water distribution networks. The method includes retrieving GIS data, asset management data, and sensor archive data of one or more assets of the utility network. The method also includes generating one or more mathematical elements from the one or more assets and creating probable connections between the one or more mathematical graph elements based on the GIS and asset data. A mathematical graph is generated based on the probable connections, the mathematical graph including one or more asset characteristics of the one or more assets. Analysis is performed on the utility network using the mathematical graph and the mathematical graph data is stored for use by other systems within the utility network.

[0010] U.S. Patent Application Publication 2011 / 0215945 describes a computerized method for monitoring a water utility network, the water utility network comprising a network of pipes for delivering water to consumers and a plurality of meters positioned within the pipes across the water distribution network. The method includes receiving meter data representing parameters measured by the meters, such as flow, pressure, chlorine level, pH and turbidity of the water being distributed through the pipes. The method also includes receiving secondary data from sources external to the meters and representing conditions affecting consumption of water in a region serviced by the water utility network such as weather and holidays. The meter and secondary data is analyzed using statistical techniques to identify water network events including leakage events and other events regarding quantity and quality of water flowing through the pipes and operation of the water network. The events are reported to users via a user interface.

[0011] European Patent Application Publication EP 1801682, to Yukawa et al., describes an information analysis system that is used for water dispenser and pipeline, the system comprises: data collection module, be used for receiving respectively from a flow meter and a data on flows that pressure indicator was sent and a pressure data with predetermined time interval, described flowmeter survey flows to the flow of the water purification the water distribution pipes network from the water dispenser pond, and described pressure indicator is measured the pressure of a pipeline of appropriate position in the described water distribution pipes network.

[0012] SUMMARY OF THE INVENTION

[0013] An embodiment of the present invention that is described herein provides a system including (a) an interface, which is configured to receive multiple time sequences of readings acquired by multiple flow sensors disposed at multiple respective locations within a distribution system of a fluid, each of the readings being indicative of a flow of the fluid flowing through one of the flow sensors, and (b) a processor, which is configured to produce a topology of the distribution system based on: (i) one or more correlations between selected pairs of the time sequences, and (ii) one or more variances between chosen pairs of the time sequences.

[0014] In some embodiments, the fluid includes water. In other embodiments, the flow includes at least one of: (i) a flow rate, and (ii) a volume, of the fluid. In yet other embodiments, the multiple time sequences include (i) a first time sequence of readings of the fluid supplied to all clients of the distribution system, which is acquired by a first flow sensor, (ii) one or more second time sequences of readings of the fluid supplied to one or more groups of clients of the distribution system, which are acquired by one or more second flow sensors, respectively, and (iii) one or more third time sequences of readings of the fluid supplied to one or more clients of each of the one or more groups, the one or more third time sequences are acquired by one or more third flow sensors, and the processor is configured to (a) define the first, second, and third flow sensors and time sequences, based on at least a comparison of the flows in the first, second and third time sequences, and (b) associate each of the third flow sensors with one of the groups.

[0015] In some embodiments, the processor is configured to associate a given third flow sensor among the third flow sensors, with a given group among the one or more groups, by performing a correlation test between the given third flow sensor and a given second flow sensor of the given group. In other embodiments, the processor is configured to (a) calculate (i) a first variance of the second time sequence of the given group that includes the third time sequence acquired by the given third flow sensor, and (ii) a second variance of the second time sequence of the given group that excludes the third time sequence acquired by the given third flow sensor, and (b) associate the given third flow sensor with the given group in response to identifying that the first variance is larger than the second variance. In yet other embodiments, the processor is configured to exclude the given third flow sensor from the given group in response to identifying that the first variance is smaller than the second variance.

[0016] In some embodiments, in response to identifying that the given third flow sensor is not associated with any of the groups of clients, the processor is configured to define the given third flow sensor as an orphan flow sensor. In other embodiments, in producing the topology, the processor is configured to (i) associate an orphan client, whose flow of the fluid flows through the orphan flow sensor, with the first flow sensor, and (ii) position the orphan flow sensor in the topology, in parallel with the one or more second flow sensors. In yet other embodiments, in producing the topology, the processor is configured to (a) (i) associate one or more of the third flow sensors with each of the second flow sensors, and (ii) not associate any of the third flow sensors with the orphan flow sensor, and (b) complete the production of the topology by associating all the third flow sensors with the respective one or more second flow sensors.

[0017] There is additionally provided, in accordance with an embodiment of the present invention, a method for producing a topology of a distribution system of a fluid, the method includes receiving multiple time sequences of readings acquired by multiple flow sensors disposed at multiple respective locations within the distribution system of the fluid, each of the readings being indicative of a flow of the fluid flowing through one of the flow sensors. The topology of the distribution system is produced based on: (i) one or more correlations between selected pairs of the time sequences, and (ii) one or more variances between chosen pairs of the time sequences.

[0018] The present invention will be more fully understood from the following detailed description of the embodiments thereof, taken together with the drawings in which: BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Fig. l is a schematic, pictorial illustration of a map of a distribution system of a fluid, in accordance with an embodiment of the present invention;

[0020] Fig. 2 is a block diagram that schematically illustrates a topology of the distribution system of Fig. 1, in accordance with an embodiment of the present invention;

[0021] Fig. 3 is a graph showing time sequences of readings acquired by multiple flow sensors disposed at multiple respective locations within the distribution system of Figs. 1 and 2, in accordance with an embodiment of the present invention; and

[0022] Fig. 4 is a flow chart that schematically illustrates a method for producing the topology of Fig. 2, in accordance with an embodiment of the present invention.

[0023] DETAILED DESCRIPTION OF EMBODIMENTS

[0024] OVERVIEW

[0025] Embodiments of the present invention that are described hereinbelow provide techniques for generating topology of a fluid (e.g., water) distribution network based on readings of water meters in the network. In some embodiments, a system for generating the topology comprises an interface and a processor. The interface is configured to receive multiple time sequences of readings acquired by multiple flow sensors disposed at multiple respective locations within the distribution system of the fluid, each of the readings being indicative of the flow of the fluid, which is flowing through one of the flow sensors.

[0026] In some embodiments, the processor is configured to produce the topology of the fluid distribution system based on: (i) one or more correlations between selected pairs of the time sequences, and (ii) one or more variances between chosen pairs of the time sequences.

[0027] In the present example, the fluid distribution system comprises (i) a first flow sensor, which is installed on the main line of the fluid distribution system, and is configured to acquire a first time sequence of readings of the fluid supplied to all the clients of the distribution system, (ii) one or more (typically multiple) second flow sensors installed on the main line that receives the fluid flowing through the first flow sensor, each of the second flow sensors is configured to acquire one or more second time sequences of readings of the fluid supplied to one or more groups of clients of the distribution system, (iii) multiple third flow sensors, which are installed on secondary lines connecting the respective clients associated within the respective groups, the third flow sensors are configured to acquire third time sequences of readings of the fluid supplied to the respective clients of each of the one or more groups, and (iv) one or more additional flow sensors, referred to herein as orphan flow sensors, which are installed on the main line (in parallel with the second flow sensors) that receives the fluid flowing through the first flow sensor. Each of the orphan flow sensors is configured to acquire a fourth time sequence of readings of the fluid supplied to a single client, also referred to herein as an orphan client.

[0028] It is noted that the second flow sensors and the orphan flow sensors are both connected to the main line, but each of the second flow sensors is connected to one or more clients of the group that are in a lower hierarchy in the distribution system, whereas the orphan flow sensor is configured to acquire the respective fourth time sequence of readings of the fluid supplied solely to the orphan client. In other words, the orphan flow sensor does not have any flow sensor that is in a lower hierarchy in the distribution system. The structure of the fluid distribution system is described in more detail in Figs. 1 and 2 below.

[0029] In some embodiments, based on the time sequences of readings acquired by the various flow sensors of the fluid distribution system, the processor is configured to define the first, second, third, and fourth flow sensors. Moreover, based on the aforementioned correlation and variance tests, the processor is configured to generate the topology of the fluid distribution system. These embodiments are described in more detail in the description of the drawings (Figs.) below.

[0030] SYSTEM DESCRIPTION

[0031] Fig. 1 is a schematic, pictorial illustration of a map 10 of a village and a water distribution system 33 of the village, in accordance with an embodiment of the present invention. Water distribution system 33 is also referred to herein as system 33, for brevity, and may alternatively be used for flowing any other suitable type of fluid, such as but not limited to sewerage of the village. Alternatively, instead of the village, map 10 may comprise a map of a factory, and system 33 may be used to flow any suitable sort of fluid used in multiple stations of the factory.

[0032] In some embodiments, map 10 comprises (i) primary water distribution lines 24, (ii) secondary water distribution lines 25, and (iii) multiple flow sensors (described in detail below) disposed along lines 24 and 25, and configured to acquire time sequences of readings indicative of the flow of the water flowing through the respective flow sensors.

[0033] In some embodiments, system 33 comprises a flow sensor 11, which is installed on the main line 24 of system 33. Flow sensor 11 is configured to acquire a time sequence of readings of the water supplied to all the clients of the distribution system 33, the time sequence acquired by flow sensor 11 is also referred to herein as a first time sequence.

[0034] In some embodiments, system 33 comprises flow sensors 12, 13, 14, 15 and 16 (also referred to herein as second flow sensors), which are installed along the main lines 24 that receives the fluid flowing through flow sensor 11. In the present example, each of flow sensors 12-16 is configured to acquire one or more-time sequences of readings of the fluid supplied to one or more groups of clients of the distribution system 33.

[0035] In some embodiments, each client of the water of system 33 has a flow meter, which is assigned to a group of clients. Each group of clients receives water passing through a predefined flow sensor among flow sensors 12-16. The client may comprise a residential house of one or more families, a commercial real estate, an industrial real estate, or any other water-consuming entity.

[0036] In the present example, flow sensor 12 receives water from flow sensor 11, and distributes the water to a given group (also referred to herein as a first group) of clients. As such, flow sensors 121, 122, 123, and 124 are installed along lines 25, at the respective clients of the first group. Each of the flow sensors 121, 122, 123 and 124 is associated with flow sensor 12, and is configured to acquire a time sequence of readings of the water supplied to a respective client of the first group. Similarly, (i) flow sensors 131, 132 and 133, which are installed along lines 25, are associated with flow sensor 13 of a second group, different from the first group, (ii) flow sensors 141 and 142, which are installed along lines 25, are associated with flow sensor 14 of a third group, different from the first and second groups, (iii) flow sensors 151 and 152, which are also installed along lines 25, are associated with flow sensor 15 of a fourth group, different from the first, second and third groups, and (iv) flow sensor 151 is installed along lines 25, and is associated with flow sensor 15 of a fifth group, different from the first, second third, and fourth groups. It is noted that the third, fourth and fifth groups are located in neighborhoods that are still being developed, and thus, have a small number of clients and respective flow sensors.

[0037] In the present example, flow sensors 12 and 13 are interconnected and configured to supply water to one another, and flow sensors 15 and 16 are also interconnected and configured to supply water to one another.

[0038] In some embodiments, the village has two water consuming factories, and system 33 comprises flow sensors 18 and 19 for the respective factories, sensors 18 and 19 are installed along the main lines 24 and receive the fluid flowing through flow sensor 11. In the present example, flow sensors 18 and 19 are also referred to herein as orphan flow sensors, as will be described herein. Each of flow sensors 18 and 19 is configured to acquire a time sequence of readings of the fluid supplied to a single client (e.g., one of the factories), also referred to herein as an orphan client. In the context of the present disclosure and in the claims, (i) the term orphan client refers to a client which is not associated with any of the groups of clients described above, and (ii) the term orphan flow sensor refers to a flow sensor installed at the respective orphan client, and configured to acquire a time sequence of reading of the water supplied solely to the respective orphan client. The differentiation between orphan sensors 18 and 19, and flow sensors 12-16 will be described in more detail in Figs. 2, 3, and 4 below.

[0039] Fig. 2 is a block diagram that schematically illustrates a topology of the distribution system 33 and a control console 35, in accordance with an embodiment of the present invention.

[0040] In some embodiments, control console 35 (also referred to herein as console 35 for brevity) is configured to produce the topology of the distribution system 33, and to control the operation of system 33. As such, control console 35 also serves as a system for producing the topology of the water distribution system 33.

[0041] In some embodiments, console 35 comprises a processor 22, in the context of the present disclosure and in the claims, the term “processor” refers to one or more of the following devices: (i) any suitable type of a central processing unit (CPU) such as but not limited to a general- purpose processor, (ii) a graphical processing unit (GPU), (iii) a tensor processing unit (TPU), (iv) a digital signal processor (DSP), and (v) any other suitable type of an application-specific integrated circuit (ASIC). At least one of, and typically all the above types of processing units may have suitable front end and interface circuits configured for interfacing and exchanging signals with (a) several modules and stations of system 33, and (b) entities external to system 33. Moreover, at least the GPU and the TPU (and optionally more of the aforementioned processing units) are configured, inter alia, to accelerate deep learning and / or machine learning workloads in one or more neural networks implemented in software and / or hardware in any suitable device of console 35.

[0042] In some embodiments, console 35 comprises an interface 20, which is configured to receive multiple time sequences of readings acquired by the flow sensors of system 33. The flow sensors are disposed at multiple respective locations within the distribution system 33, as will be described in more detail below. In some embodiments, each of the readings (in the time sequences) being indicative of the flow of the water, which is flowing in lines 24 and / or 25 through one of the flow sensors. An example of the time sequences is shown and described in detail in Fig. 3 below.

[0043] In some embodiments, processor 22 is configured to produce the topology of the water distribution system 33 based on: (i) one or more correlations between selected pairs of the time sequences, and (ii) one or more variances between chosen pairs of the time sequences, as will be described in detail in Fig. 3 below. In some embodiments, console 35 comprises a display device, referred to herein as a display 17, which is configured to display data and images received from processor 22, or inputs inserted by a user (not shown) using input devices 29. It is noted that the configuration of console 35 is provided by way of example, and in other embodiments, console 35 may have any other suitable configuration.

[0044] In some embodiments, processor 22 is configured to display on display 17, a digital image 21 comprising map 10 or one or more segments thereof. Additionally, or alternatively, processor 22 is configured to display on display 17 the topology of system 33, which is described herein.

[0045] Reference is now made to the topology of system 33. In some embodiments, flow sensor 11, which is installed on the primary (i.e., main) water supply line 24 of system 33, is configured to acquire the time sequence of readings of the water supplied to all the clients of the water distribution system 33, as described in Fig. 1 above. Flow sensors 12-16, and orphan flow sensors 18 and 19, are also installed on the primary water supply line 24 of system 33 and receive the water passed through flow sensor 11. Moreover, the groups of clients are arranged along the respective secondary water distribution lines 25.

[0046] In such embodiments, flow sensors 121, 122, 123, 124 and 124 are installed at the respective clients of the first group. As such, flow sensors 121, 122, 123 and 124 are associated with flow sensor 12, and are configured to acquire time sequences of readings of the water supplied to the respective clients of the first group. The flow sensors of the second, third, fourth and fifth groups are installed along the secondary water line 25, and are associated with flow sensors 13, 14, 15 and 16, respectively, as described in Fig. 1 above.

[0047] In the present example, the hierarchy of system 33 is defined along the downstream of the water. As such, (i) flow sensor 11 is at the top of the hierarchy, (ii) flow sensors 12-16, 18, 19 are one level below flow sensor 11, and receive the water passing through flow sensor 11, and (iii) the other flow sensors are associated with flow sensors 12-16 and are installed along line 25, are at the lowest level of the hierarchy. It is noted that in this configuration, flow sensors 12-16, and orphan flow sensors 18 and 19, are both connected to the primary line 24, but each of flow sensors 12-16 is connected to one or more clients of the respective group, whereas orphan flow sensors 18 and 19 do not have any flow sensors that are in a lower hierarchy in the water distribution system 33.

[0048] In some embodiments, all the flow sensors of system 33 are electrically connected to console 35 via cables 26, and interface 20 is configured to receive from the flow sensors of system 33, signals indicative of the flow of the water. In the context of the present disclosure and in the claims, the term “flow” refers to at least one of the flow rate of the water, and the volume of the water flowing through the respective flow sensor.

[0049] In some embodiments, based on the signals received from the flow sensors, processor 22 is configured to generate time sequences of readings acquired by each of the flow sensors of system 33. Processor 22 is further configured to analyze the time sequences of readings from each sensor, and to generate the topology of system 33.

[0050] In some embodiments, the largest volume of water pass through flow sensor 11, and therefore, flow sensor 11 is defined as the flow sensor having the highest hierarchy. The volume of water passing though flow sensors 12-16, 18 and 19 is smaller than that passing through flow sensor 11, but are typically larger than that of the flow sensors within the groups associated with flow sensors 12-16. Moreover, in order to associate flow sensors 12-16, 18 and 19 with flow sensor 11, the time sequence of readings of each of flow sensors 12-16, 18 and 19 must be correlative with that of flow sensor 11, as will be described in Fig. 3 below. In such embodiments, processor 22 is configured to define flow sensors 12-16, 18 and 19 in the second level of hierarchy, below flow sensor 11 that is defined in the first level of hierarchy. Processor 22 is further configured to define orphan flow sensors 18 and 19, and the hierarchy of each flow sensor of system 33 based on correlation and variance test described in Fig. 3 below.

[0051] Fig. 3 is a graph showing time sequences of readings acquired by flow sensors 13, 18, 19, 131 and 142 disposed at multiple respective locations within water distribution system 33, in accordance with an embodiment of the present invention. It is noted that the description of Fig. 3 assumes no loss of water due to leaks or other malfunctioning in system 33.

[0052] In some embodiments, processor 22 is configured to produce graph 30 based on the time sequences of readings acquired by flow sensors 13, 18, 19, 131 and 142. In the present example, graph 30 presents the flow rate (in the vertical axis) as a function of time (in the horizontal axis). Due to the different scale of flow rates of readings acquired by flow sensors 13 and 18 compared to that of flow sensors 19, 142 and 131, graph 30 has two axes of time in order to compensate for the different scale of flow rates, and to show the time sequences of readings acquired by all flow sensors 13, 18, 19, 131 and 142 over graph 30.

[0053] In some embodiments, processor 22 is configured to check the correlation between each pair of flow sensors of system 33. For example, in sections 32 and 36 of graph 30, the flow rate in flow sensors 13 and 131 is dropped to zero, thus, processor 22 associates flow sensor 131 with flow sensor 13. Moreover, the flow rate readings received from flow sensors 18, 19, and 142 is larger than zero. Thus, flow sensors 18, 19, and 142 could not be associated with flow sensor 13, because they could not sense the flow of water when no water is flowing through flow sensor 13.

[0054] Moreover, in a section 34 of graph 30, the flow rate in flow sensor 13 trends up to a local peak and subsequently trends down, and in a section 38 of graph 30, the flow rate in flow sensor 13 trends down. In some embodiments, processor 22 is configured to use these trends to produce the topology by checking the variance between pairs of time sequences, as will be described herein.

[0055] Reference is now made to insets 40 and 42 showing a graphical representation of an analysis of variance based on the time sequence readings in section 34. In some embodiments, in inset 40, processor 22 is configured to plot the variance between (i) the flow rate in flow sensor 13, and (ii) the combined flow rates in flow sensors 13 and 19. Moreover, in inset 42, processor 22 is configured to plot the variance between (i) the flow rate in flow sensor 13, and (ii) the combined flow rates in flow sensors 13 and 131. As shown in the examples of insets 40 and 42, it is noted that the variance is (a) increased when combining the flow rates in flow sensors 13 and 19, and (b) reduced when combining the flow rates in flow sensors 13 and 131. In some embodiments, based on the examples of insets 40 and 42, processor 22 is configured to associate flow sensor 131 with flow sensor 13, and not to associate flow sensor 19 with flow sensor 13.

[0056] In some embodiments, processor 22 is configured to perform the correlation analysis and the variance analysis between any pairs of graphs, wherein each graph of the pair may comprise the flow rate reading received from one or more flow sensors and / or a combination of flow readings from multiple flow sensors, at some or all the sections of graph 30. In other words, by comparing the variance, within a predefined section of graph 30, in the readings of (i) flow sensor 13, and (ii) a combination of flow sensor 13 and an additional flow sensor, processor is configured to determine whether or not the additional flow sensor is associated with flow sensor 13.

[0057] In some embodiments, the flow sensors that are (i) not correlated with any of flow sensors 12-16, and / or (ii) increase the variance in flow sensors 12-16, and (iii) do not have any flow sensor associated therewith, are defined as orphan flow sensors, such as flow sensors 18 and 19.

[0058] In some embodiments, some of flow sensors 12-16 may be interconnected along line 24 and / or line 25, for example, flow sensors 12 and 13 are interconnected, and flow sensors 15 and 16 are interconnected, as described in Fig. 2 above. Based on the correlation analysis and the analysis of variance, processor 22 is configured to assign flow sensors 12 and 13 into different groups. In such embodiments, based on the correlation and variance analysis shown in graph 30, processor 22 is configured to associate flow sensors to respective groups, and to define orphan flow sensors that cannot be associated with any of the groups.

[0059] In some embodiments, based on the technique described above, processor 22 is configured to determine the orphan flow sensors regardless of their absolute flow rates. In the present example, the flow rate of orphan flow sensor 18 is higher than that of flow sensor 13, and the flow rate of orphan flow sensor 19 is substantially lower than that of flow sensor 13, and both flow sensors 18 and 19 are defined as orphan flow sensors based on the analysis of correlation and the analysis of variance that are described in detail above.

[0060] In some embodiments, each of the third flow sensors, in the present example flow sensors 121-124, 131-133, 141, 142, 151, 152, and 161, is configured to transmit its fluid (e.g., water) consumption data during a predefined time interval, for example every hour. Based on these readings, processor 22 is configured to (i) generate a third time sequence of readings of the fluid supplied to the respective end-client in system 33, and (ii) estimate the daily water consumption. Similarly, each of the second flow sensors, in the present example flow sensors 12-19, is configured to transmit its fluid (e.g., water) consumption data regardless of the flow direction, e.g., every hour. Based on these readings, processor 22 is configured to (i) generate a second time sequence of readings of the fluid supplied to the respective group of clients in system 33, and (ii) estimate the daily water consumption of the respective group. Moreover, flow sensor 11 is configured to transmit its fluid (e.g., water) consumption data during a predefined time interval, for example every hour. Based on these readings, processor 22 is configured to (i) generate a first time sequence of readings of the fluid supplied to all the endclients of distribution system 33, and (ii) estimate the daily water consumption of distribution system 33.

[0061] In some embodiments, processor 22 is configured to generate for each flow sensor of each layer (first, second, and third) of time sequences, an hourly summary and a daily summary of the fluid consumption. Based on the time sequencies, processor 22 is configured to identify loss of fluid in distribution system 33. In the context of the present disclosure, the term loss refers to any fluid consumption which is not metered by all sensors. The fluid loss may comprise, for example, leaks and one or more events of consumption, as will be described herein. As such, a continuous fluid consumption in a given flow sensor is indicative of a leak, and an event of opening of a fire extinguishing hydrant is still loss but not a leak. For example, (i) a continuous consumption in flow sensors 11, 12, and 121 is indicative of a leak in the client of flow sensor 121, and (ii) a continuous consumption in flow sensors 11 and 12, but not in any of flow sensors 121-124 is indicative of a leak between flow sensor 12 and the group of flow sensors 121-124. Moreover, in the present example processor 22 is configured to identify loss (due to continuous leak or events such as temporary openings of the fire extinguishing hydrant) by comparing, e.g., the daily or hourly summary of the fluid consumption between (i) flow sensor 12, and (ii) a summary of the consumption by flow sensors 121-124. Based on these techniques processor 22 is configured to filter out loss of fluid (as well as other events, such as but not limited to faulty sensors, and power outage) while generating the topology of system 33.

[0062] Fig. 4 is a flow chart that schematically illustrates a method for producing the topology of system 33, in accordance with an embodiment of the present invention.

[0063] The method begins at a time sequence receiving step 100 with interface 20 receiving from all the flow sensors of system 33, the signals indicative of the flow of water, and processor 22 producing the time sequences of flow rate readings, as described in detail in Figs. 2 and 3 above.

[0064] At a correlation estimation step 102, processor 22 is configured to analyze and estimate the correlation between selected pairs of the time sequences, as described in detail in Fig. 3 above.

[0065] At a variance estimation step 104, processor 22 is configured to analyze and estimate the variance between chosen pairs of the time sequences. It is noted that the selected pairs of step 102 may be different from the chosen pairs of step 104. For example, (i) in the correlation analysis, processor 22 compares the time sequences of flow rate readings between sensor 13 and sensor 142, and (ii) in the variance analysis, processor 22 compares the time sequences of flow rate readings between (a) sensor 13, and a combination of sensors 13 and 19, as shown and described in detail in Fig. 3 above. Moreover, flow sensors that are not associated with any of the groups, and do not have any flow sensor associated therewith, are determined by processor 22 as orphan flow sensors of system 33, such as flow sensors 18 and 19, as described in detail in Fig. 3 above.

[0066] At a topology production step 106 that concludes the method, processor 22 is configured to produce the topology of system 33 (shown in Fig. 3 above) based on (i) the flow rate reading received from each flow sensor of system 33 (as described in detail in Figs. 2 and 3 above), (ii) the estimated correlations as described in detail in Fig. 3 above, and (iii) the estimated variances, as described in detail in Fig. 3 above.

[0067] Although the embodiments described herein mainly address topology of water distribution systems in villages, cities, and countries, the methods and systems described herein can also be used in other applications, such as in any other suitable type of fluid, such as but not limited to sewerage of the village / city / country, and distribution of fluids (e.g., liquids and / or gases), such as but not limited to oil and gas in factories and between factories. Moreover, the disclosed techniques may be used for scaling (i.e., expending) the distribution system of any fluids, and identifying the flow cycles of such fluids may be used to build scenarios of expected faults in the water network, for example, an increase in pressure and / or an increase in the wear and / or damage occurred in the pipelines of the distribution system.

[0068] It will thus be appreciated that the embodiments described above are cited by way of example, and that the present invention is not limited to what has been particularly shown and described hereinabove. Rather, the scope of the present invention includes both combinations and sub-combinations of the various features described hereinabove, as well as variations and modifications thereof which would occur to persons skilled in the art upon reading the foregoing description and which are not disclosed in the prior art. Documents incorporated by reference in the present patent application are to be considered an integral part of the application except that to the extent any terms are defined in these incorporated documents in a manner that conflicts with the definitions made explicitly or implicitly in the present specification, only the definitions in the present specification should be considered.

Claims

AMENDED CLAIMS received by the International Bureau on 25 November 2025 (25.11.2025)1. A system, comprising: an interface, which is configured to receive multiple time sequences of readings acquired by multiple flow sensors comprising a first flow sensor, one or more second flow sensors and one or more third flow sensors that are disposed at multiple respective locations within a distribution system of a fluid, each of the readings being indicative of a flow of the fluid flowing through one of the flow sensors; and a processor, which is configured to produce a topology of the distribution system based on: (i) one or more correlations between selected pairs of the time sequences, and (ii) one or more variances between chosen pairs of the time sequences, wherein the processor is configured to associate a given third flow sensor among the third flow sensors, with a given group by calculating a first variance of a second time sequence that includes the third time sequence and a second variance of the second time sequence that excludes the third time sequence, and associate the given third flow sensor with the given group in response to identifying that the first variance is larger than the second variance.

2. The system according to claim 1, wherein the fluid comprises water.

3. The system according to claim 1, wherein the flow comprises at least one of: (i) a flow rate, and (ii) a volume, of the fluid.

4. The system according to any of claims 1-3, wherein the multiple time sequences comprise (i) a first time sequence of readings of the fluid supplied to all clients of the distribution system, which is acquired by the first flow sensor, (ii) one or more second time sequences of readings of the fluid supplied to one or more groups of clients of the distribution system, which are acquired by the one or more second flow sensors, respectively, and (iii) one or more third time sequences of readings of the fluid supplied to one or more clients of each of the one or more groups, the one or more third time sequences are acquired by the one or more third flow sensors, and wherein the processor is configured to (a) define the first, second, and third flow sensors and time sequences, based on at least a comparison of the flows in the first, second and third time sequences, and (b) associate each of the third flow sensors with one of the groups.

5. The system according to claim 4, wherein the processor is configured to associate the given third flow sensor with the given group among the one or more groups, by performing a correlation test between the given third flow sensor and a given second flow sensor of the given group.

6. The system according to claim 5, wherein the processor is configured to exclude the given third flow sensor from the given group in response to identifying that the first variance is smaller than the second variance.

7. The system according to claim 6, wherein in response to identifying that the given third flow sensor is not associated with any of the groups of clients, the processor is configured to define the given third flow sensor as an orphan flow sensor.

8. The system according to claim 7, wherein in producing the topology, the processor is configured to (i) associate an orphan client, whose flow of the fluid is flowing through the orphan flow sensor, with the first flow sensor, and (ii) position the orphan flow sensor in the topology, in parallel with the one or more second flow sensors.

9. The system according to claim 8, wherein in producing the topology, the processor is configured to (a) (i) associate one or more of the third flow sensors with each of the second flow sensors, and (ii) not to associate any of the third flow sensors with the orphan flow sensor, and (b) complete the production of the topology by associating all the third flow sensors with the respective one or more second flow sensors.

10. A method for producing a topology of a distribution system of a fluid, the method comprising: receiving multiple time sequences of readings acquired by multiple flow sensors comprising a first flow sensor, one or more second flow sensors and one or more third flow sensors that are disposed at multiple respective locations within the distribution system of the fluid, each of the readings being indicative of a flow of the fluid flowing through one of the flow sensors; and producing the topology of the distribution system based on: (i) one or more correlations between selected pairs of the time sequences, and (ii) one or more variances between chosen pairs of the time sequences, wherein producing the topology comprises associating a given third flow sensor among the third flow sensors, with a given group by calculating a first variance of a second time sequence that includes the third time sequence and a second variance of the second time sequence that excludes the third time sequence, and associating the given third flow sensor with the given group in response to identifying that the first variance is larger than the second variance.

11. The method according to claim 10, wherein the fluid comprises water.

12. The method according to claim 10, wherein the flow comprises at least one of: (i) a flow rate, and (ii) a volume, of the fluid.

13. The method according to any of claims 10-12, wherein receiving the multiple time sequences comprises receiving (i) a first time sequence of readings of the fluid supplied to all clients of the distribution system, which is acquired by the first flow sensor, (ii) one or more second time sequences of readings of the fluid supplied to one or more groups of clients of the distribution system, which are acquired by the one or more second flow sensors, respectively, and (iii) one or more third time sequences of readings of the fluid supplied to one or more clients of each of the one or more groups, the one or more third time sequences are acquired by the one or more third flow sensors, and wherein producing the topology comprises: (a) defining the first, second, and third flow sensors and time sequences, based on at least comparing the flows in the first, second and third time sequences, and (b) associating each of the third flow sensors with one of the groups.

14. The method according to claim 13, wherein associating each of the third flow sensors comprises associating the given third flow sensor with the given group among the one or more groups, by performing a correlation test between the given third flow sensor and a given second flow sensor of the given group.

15. The method according to claim 14, and comprising excluding the given third flow sensor from the given group, in response to identifying that the first variance is smaller than the second variance.

16. The method according to claim 15, wherein producing the topology comprises defining the given third flow sensor as an orphan flow sensor, in response to identifying that the given third flow sensor is not associated with any of the groups of clients.

17. The method according to claim 16, wherein producing the topology comprises associating an orphan client, whose flow of the fluid is flowing through the orphan flow sensor, with the first flow sensor, and positioning the orphan flow sensor in the topology, in parallel with the one or more second flow sensors.

18. The method according to claim 17, wherein producing the topology comprises (a) (i) associating one or more of the third flow sensors with each of the second flow sensors, and (ii) not associating any of the third flow sensors with the orphan flow sensor, and (b) completingthe production of the topology by associating all the third flow sensors with the respective one or more second flow sensors.

Images