Digital twin intelligent water saving system based on distributed optical fiber sensing network

Abstract

The invention discloses a digital twin intelligent water-saving system based on a distributed optical fiber sensing network, which belongs to the technical field of water-saving management and specifically comprises the distributed optical fiber sensing network laid along a water delivery pipeline in a tree topology; the water use event recognition module collects optical fiber vibration signals, converts the optical fiber vibration signals into digital waveforms and recognizes trigger points through an amplitude threshold value; the water supply topology construction module constructs a water supply dependency topological graph containing nodes and directed edges according to the spatial position and time delay of the trigger point; a hydraulic model generation module superposes the topological graph and the digital map of the water delivery pipeline to generate a dynamic hydraulic balance model containing node water intensity weight coefficients; the intelligent water-saving control module sends a periodic intermittent closing instruction to the intelligent water valve of the low-weight node according to the node weight change, and the duration of the instruction is in direct proportion to the weight difference value of the adjacent node; according to the invention, refined intelligent water-saving management of a centralized water consumption scene is realized.

Description

Technical Field

[0001] The present invention relates to the technical field of water-saving management, and in particular to a digital twin intelligent water-saving system based on a distributed optical fiber sensing network. Background Art

[0002] Water pipeline networks in urban centralized water supply scenarios are becoming increasingly complex, with multi-level branching characteristic of water lines in campuses, residential areas, industrial parks, and business centers. Distributed fiber optic sensing technology, with its long-distance continuous sensing capabilities, has been applied to pipeline physical condition monitoring, locating leaks by capturing anomalies in vibration signals. However, existing technologies primarily focus on post-leakage management and lack effective technical means for systematic water conservation in pipeline networks.

[0003] Current smart water-saving systems rely primarily on two basic architectures: one based on discretely installed smart metering terminals, which collect data from endpoints to build water usage analysis models; the other employs arrays of fixed pressure sensors to locate leaks based on pressure fluctuations in the pipe network. Some systems incorporate a digital twin framework, mapping the physical pipe network structure into a computational model and adjusting valve openings or pump station power based on the simulation results. Related research proposes using data from multiple sensor types to construct a digital mirror of the pipe network and to control water supply equipment through hydraulic model calculations.

[0004] Existing methods are still constrained by the following technical characteristics: First, the point-sensing deployment model requires a large amount of hardware facilities, resulting in a significant increase in system construction costs and the problem of insufficient monitoring continuity; second, the topological structure of the digital twin model relies on a preset pipe network diagram, and when the actual water supply path changes due to valve switching, it cannot automatically update the hierarchical relationship; more importantly, the current technology only triggers a response when a clear leak signal or abnormal water consumption is detected, and fails to implement pre-emptive water-saving intervention based on the dynamic topological relationship of the water supply network. Especially in a multi-branch pipe network environment, existing solutions have not yet broken through the technical bottleneck of automatically constructing a real-time water supply dependency structure through continuous sensing data, and also lack an effective mechanism to directly convert dynamic topological relationships into water-saving control strategies. These technical characteristics restrict the fundamental improvement of water-saving efficiency. Summary of the Invention

[0005] The purpose of this invention is to provide a digital twin intelligent water-saving system based on a distributed optical fiber sensing network to solve the following technical problems: The point sensing deployment model of existing methods is costly, and the digital twin topology relies on preset drawings and cannot be automatically updated, lacking prior intervention based on dynamic topology.

[0006] The purpose of the present invention can be achieved through the following technical solutions: A digital twin intelligent water-saving system based on a distributed optical fiber sensing network, comprising: The distributed fiber optic sensing network consists of a single trunk fiber and multiple branch fibers forming a tree topology, and is laid continuously along the physical path of the water pipeline; The water use event recognition module is used to collect optical fiber vibration signals in real time and convert them into digital waveform sequences, and identify water use event trigger points by setting waveform amplitude thresholds; The water supply topology construction module is used to automatically construct a water supply dependency topology diagram between water-using units based on the spatial location of the water-using event trigger point and the time delay relationship between adjacent trigger points. The nodes in the topology diagram represent water-using units, and the directed edges in the topology diagram represent the water supply direction. A hydraulic model generation module is used to spatially superimpose the water supply dependency topology map with the preset water pipeline digital map to generate a dynamic hydraulic balance model, which includes a weight coefficient of the water use intensity of each node; The intelligent water-saving control module is used to send a periodic intermittent closing instruction sequence to the intelligent water valve associated with the low-weight coefficient node according to the real-time change trend of the node weight coefficient in the dynamic hydraulic balance model, when no physical leakage occurs. The duration of the instruction sequence is proportional to the difference in the weight coefficients of adjacent nodes.

[0007] As a further solution of the present invention: in the water supply topology construction module, the process of constructing the water supply dependency topology map is: When a water use event trigger point is detected at the end of the branch optical fiber, the first vibration peak time of the water use event trigger point is recorded; if the vibration waveform similarity of the sensing point closest to the branch optical fiber end on the trunk optical fiber exceeds the threshold within the set time window, it is determined that the branch node depends on the trunk node for water supply; For branch nodes at the same level, if the triggering time interval between two branch nodes is less than the propagation time of the vibration wave in the pipeline, and the waveform envelope of the downstream branch node matches the attenuation shape of the upstream branch node, a directed edge is established from the upstream branch node to the downstream branch node. After all dependencies are determined, the node groups with the same water supply source are merged to form a hierarchical topology. The top node of the hierarchical topology is the main water supply entrance of the park, and the bottom node of the hierarchical topology is the terminal water use unit.

[0008] As a further solution of the present invention: the method for determining the similarity of the vibration waveform is: The original vibration waveform of a fixed time length before and after the trigger point of the branch node is intercepted as the sequence to be matched, and the vibration waveform of the corresponding time window of the candidate trunk fiber node is simultaneously intercepted as the reference sequence; the length of the time window is calculated by dividing the physical distance between the branch fiber and the trunk fiber by the water hammer wave velocity under the pipe diameter; The sequence to be matched and the reference sequence are aligned nonlinearly along the time axis, and the minimum cumulative distance on the alignment path is calculated. When the minimum cumulative distance is less than the reference value of the sound wave propagation loss determined by the pipeline material, the waveform similarity is determined to meet the standard.

[0009] As a further solution of the present invention: in the hydraulic model generation module, the process of constructing the digital map of the water pipeline is as follows: Identify characteristic vibration modes of pipe fittings through optical fiber vibration signals. These include vortex-induced vibration waveforms at elbows, water hammer wavefront characteristics during valve opening and closing, and specific frequency harmonics during pump startup. The position of pipe fittings is located according to the spatial distribution of characteristic vibration modes; the actual length of the pipeline section is inverted using the time difference of vibration wave propagation in continuous pipeline sections; and a three-dimensional pipeline model with topological attributes is generated after comparing the identification results with the design drawings. The update cycle of the three-dimensional pipeline model is synchronized with the water supply dependency topology map.

[0010] As a further solution of the present invention: in the hydraulic model generation module, the process of generating the dynamic hydraulic balance model is: Using the water supply dependency topology map as the basic framework, the pipe diameter change points, pump station locations, and reservoir coordinate information in the digital map of the water supply pipeline are superimposed; an initial weight coefficient is assigned to each node in the water supply dependency topology map, and the initial weight coefficient value is determined by the water use unit type associated with the node; the number of water use event triggering events per unit time at each node is counted in real time, and the water use intensity is calculated based on the waveform integral area corresponding to each water use event triggering; the water use intensity data updates the node weight coefficient in a sliding time window manner, and the nodes whose weight coefficient change rate exceeds the threshold are automatically marked as abnormal nodes; when the weight coefficient ratio between adjacent level nodes continuously deviates from the square of the pipe diameter ratio, the topology structure verification process is triggered.

[0011] As a further solution of the present invention: In the intelligent water-saving control module, the process of generating a periodic intermittent shutdown instruction sequence is as follows: Obtain the weight coefficient change curve of the target node in the dynamic hydraulic balance model for several consecutive time periods, and extract the stable stage and rising stage in the weight coefficient change curve; Generate a shutdown instruction in the stable phase, and the duration of the shutdown instruction is equal to the historical average water consumption interval of the target node multiplied by the weight coefficient attenuation factor; insert a pre-shutdown instruction before the rising phase, and the duration of the pre-shutdown instruction is negatively correlated with the rising slope of the weight coefficient; For brother nodes that rely on the same water supply source, a staggered shutdown schedule is generated after the brother nodes are arranged in ascending order according to their weight coefficients. The start-up time interval of the shutdown instructions of adjacent nodes in the staggered shutdown schedule is greater than the time required for the water pressure fluctuation to stabilize.

[0012] As a further solution of the present invention: the weight coefficient attenuation factor is calculated as follows: Establish a correlation function between the target node weight coefficient and the standard deviation of the weight coefficients of other nodes at the same level. When the standard deviation is less than the threshold, a fixed attenuation factor is used. When the standard deviation is greater than the threshold, the attenuation factor is dynamically adjusted according to the degree of deviation between the target node and the average weight coefficient. That is, the attenuation factor is increased when the target node weight coefficient is lower than the average weight coefficient, and the attenuation factor is reduced when the target node weight coefficient is higher than the average weight coefficient. The adjustment amplitude of the attenuation factor is inversely proportional to the hierarchical depth from the target node to the root node in the water supply dependency topology diagram.

[0013] As a further solution of the present invention, a meteorological data fusion module is also included, specifically: Real-time access to rainfall intensity, evaporation, and sunshine duration data from regional meteorological stations, converting rainfall intensity, evaporation, and sunshine duration data into regional water demand compensation coefficients; When the regional water demand compensation coefficient continues to be lower than the threshold, a virtual water source node is added to the dynamic hydraulic balance model. The weight coefficient of the virtual water source node is negatively correlated with the regional water demand compensation coefficient. A bidirectional connection edge is established between the virtual water source node and the physical reservoir node, triggering the intelligent water valve opening priority redistribution strategy.

[0014] As a further solution of the present invention: the function of the virtual water source node is: When the regional water demand compensation coefficient decreases, the virtual water source node automatically increases its weight coefficient value. The weight coefficient increase value is transmitted from top to bottom according to the hierarchical structure of the water supply dependency topology graph. During the transmission process, each time a node in the water supply dependency topology graph is passed, the weight coefficient increase value is attenuated in equal parts according to the number of node out-degrees. When the deviation between the actual water level sensor data of the physical reservoir node and the theoretical water level calculated by the virtual water source node exceeds the tolerance, the water supply dependency topology reconstruction process is triggered.

[0015] Beneficial effects of the present invention: This invention replaces traditional point-based sensing by continuously laying a distributed fiber-optic sensor network with a tree-like topology along the water pipeline. This significantly reduces hardware deployment costs while enabling real-time monitoring of the entire water pipeline, resolving the issue of discontinuous point-based monitoring. Based on the spatial location and time delay relationship between water use event trigger points, a dynamic water supply dependency topology is automatically constructed. This hierarchical structure can be autonomously updated as the actual water supply path changes, eliminating the digital twin topology's reliance on pre-set diagrams and forming a real-time water supply structure that matches the actual pipeline network. This topology is overlaid with a digital map of the water pipeline to generate a dynamic hydraulic balance model. Node weight coefficients are dynamically adjusted based on water use intensity, accurately mapping the physical pipeline network state. Based on the weight coefficient trend, periodic intermittent shutdown commands proportional to the weight difference between adjacent nodes are sent to low-weight nodes. This allows for preemptive water conservation intervention through peak-shifting control, reversing the existing passive response model of leaks or water exceeding standards. Meteorological data is incorporated to generate regional water demand compensation coefficients, dynamically adjusting water supply strategies through virtual water source nodes to improve the system's adaptability to environmental changes. Through the synergistic effect of the above technologies, the present invention comprehensively improves water-saving efficiency and is suitable for refined water management in multiple scenarios such as campuses, residential areas, and parks. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The present invention will be further described below with reference to the accompanying drawings.

[0017] Figure 1 It is a module schematic diagram of the present invention. DETAILED DESCRIPTION

[0018] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making any creative efforts shall fall within the scope of protection of the present invention.

[0019] See also Figure 1 As shown, the present invention is a digital twin intelligent water-saving system based on a distributed optical fiber sensing network, comprising: The distributed fiber-optic sensing network utilizes a tree-like topology, consisting of a single trunk fiber and multiple branch fibers, laid continuously along the physical path of the water pipeline. The trunk fiber covers the main water supply line, while the branch fibers extend to each terminal water consumption unit, forming a continuous, global monitoring network that comprehensively captures vibration signals within the pipeline, providing essential data for subsequent analysis.

[0020] The water use event recognition module collects vibration signals transmitted in real time via the distributed fiber optic network. These signals originate from various dynamic changes in water flow within the pipeline, such as the impact of water flow when a terminal water unit is activated, the water hammer effect caused by valve opening and closing, and the continuous disturbances caused by the operation of water-using equipment. The module converts the collected analog vibration signals into a digital waveform sequence that can be quantified and analyzed. During this process, basic signal noise reduction is performed simultaneously to filter out irrelevant interference such as ambient noise. The module then identifies valid water use events based on preset waveform amplitude thresholds. Different water use scenarios generate characteristic vibration amplitudes. For example, the waveform amplitude when a high-flow water device is activated is typically higher than that of daily low-flow water use. The module sets differentiated thresholds accordingly. When the vibration waveform amplitude at a specific location exceeds the corresponding threshold, it is identified as a water use event trigger point. The module not only records the precise time of the event but also, combined with the spatial distribution information of the fiber optic sensing points, accurately marks the trigger point's physical location within the pipeline, providing accurate event data for subsequent topology construction.

[0021] The water supply topology construction module operates based on the spatial location of the trigger points of water use events and the time delay relationship between adjacent trigger points. The system first determines the specific location of each trigger point in the physical pipeline. It then analyzes the time difference between adjacent trigger points, such as the vibration signal delay between the trigger point at the end of a branch fiber and the corresponding sensor point on the trunk fiber, to determine the direction of water supply and construct a water supply dependency topology. Nodes in the diagram represent water use units, and directed edges indicate the direction of water supply. Ultimately, a hierarchical structure is formed from the main water supply inlet to the terminal water use unit, and it can dynamically adjust as the actual water supply path changes.

[0022] The hydraulic model generation module spatially overlays the water supply dependency topology with a pre-set digital map of water pipelines. The digital map contains physical information such as pipe diameter change points, pump station locations, and reservoir coordinates. The two are integrated to generate a dynamic hydraulic balance model. The model assigns a weight coefficient to each node, which is updated in real time based on indicators reflecting water use intensity, such as the number of water use events per unit time and the integrated waveform area. This ensures that the virtual model accurately reflects the real-time status of the physical pipeline network.

[0023] The intelligent water-saving control module operates based on the real-time trends of node weight coefficients in the dynamic hydraulic balance model. When a low-weight node—a unit with low water intensity or room for optimization—is identified, the module sends a periodic sequence of intermittent shutdown commands to its associated intelligent water valves. The duration of these commands is related to the difference in weight coefficients between adjacent nodes; a larger difference results in a longer shutdown period. Furthermore, the module uses staggered peak control to avoid water pressure fluctuations caused by simultaneous valve closures in the same area. Proactively intervening in the absence of physical leaks reduces ineffective water consumption.

[0024] In the water supply topology construction module, the process of constructing the water supply dependency topology map is as follows: When a water use event trigger point is detected at the end of a branch fiber, the module immediately records the time of the first vibration peak at that trigger point. This time stamp is a key benchmark for determining the direction of water supply flow, as water propagating through the pipeline forms vibration waves, and the time difference between the source and the end directly reflects the path correlation. The system then focuses on the sensing point on the trunk fiber closest to the end of the branch fiber and monitors changes in its vibration signal within a set time window. The time window must be set based on the physical characteristics of the pipeline to ensure that it covers a reasonable length of time for the vibration wave to propagate from the trunk to the branch. This avoids missing valid signals due to a window that is too short and prevents irrelevant interference from being introduced due to a window that is too long. If a trigger point with a vibration waveform similarity exceeding a threshold at the trunk sensing point appears within the window, it indicates a clear correlation between the two vibration signals. This determines that the branch node relies on the trunk node for water supply, thereby establishing a basic connection from the trunk node to the branch node in the topology map.

[0025] For branch nodes at the same level, the module adopts a more sophisticated association judgment logic. When water use event trigger points appear successively at two branch nodes at the same level, the system first calculates the trigger time interval between the two and compares it with the propagation time of the vibration wave in the pipeline. If the trigger time interval is less than the propagation time, it means that the vibration signal of the previous node has enough time to be transmitted to the next node, and there is a possibility of water supply association. Next, the system will perform a morphological analysis on the vibration waveforms of the two nodes, focusing on comparing the waveform envelope morphology of the downstream branch node with the waveform attenuation morphology of the upstream branch node. Since when water flows in the pipeline at the same level, the waveform will show a specific attenuation law due to factors such as friction and changes in pipe diameter. If the morphology of the two matches, it can be confirmed that there is a direct water supply transmission relationship, and then a directed edge from the upstream branch node to the downstream branch node is established in the topology graph.

[0026] After the dependency relationships between all nodes are determined, the module will group and merge nodes with the same water supply source. For example, if multiple branch nodes all rely on the same trunk node for water supply, they will be classified into the same node group to simplify the topology and highlight the hierarchical relationship. In the final hierarchical topology, the top-level node corresponds to the main water supply entrance of the campus, which serves as the source of the entire water supply network; the bottom-level nodes correspond to each terminal water-using unit, such as the dormitory faucet on campus, the workshop equipment interface in the park, etc. The middle-level nodes are distributed in sequence according to the branch relationship of the actual water supply path to ensure that the topology diagram can fully and accurately reflect the hierarchical structure of the physical pipe network.

[0027] Determining the similarity of vibration waveforms is a key step in ensuring the accurate establishment of water supply dependency relationships. Through refined waveform comparison, the influence of interference signals on correlation determination can be eliminated. Specifically: First, the original vibration waveform of a fixed length before and after the trigger point of the branch node is intercepted as the sequence to be matched. This sequence encompasses the complete vibration process triggered by the water use event and serves as the basis for feature extraction. Simultaneously, the vibration waveform of the corresponding time window of the candidate trunk fiber node is intercepted as a reference sequence. The time window length of the reference sequence is determined by the physical distance between the branch fiber and the trunk fiber and the water hammer wave velocity under the pipe diameter. This ensures that the two sequences are comparable in the time dimension and accurately reflect the propagation correlation of the vibration wave.

[0028] Subsequently, the system performs nonlinear time axis alignment on the intercepted sequence to be matched and the reference sequence. Since when the vibration wave propagates in pipelines of different materials and different diameters, the waveform may be offset on the time axis due to differences in attenuation speeds. Nonlinear alignment can eliminate the effect of this offset, so that the characteristic waveforms of the two sequences accurately correspond in the time dimension. On this basis, the minimum cumulative distance on the alignment path is calculated. This value reflects the overall similarity of the two waveforms. The smaller the value, the closer the waveform characteristics are. When the minimum cumulative distance is less than the reference value of the sound wave propagation loss determined by the pipeline material, it is determined that the waveform similarity meets the standard. Different pipeline materials have different loss characteristics during the sound wave propagation process. The setting of this reference value fully considers the influence of the material on the vibration signal, ensuring that the standard for similarity determination matches the actual pipeline characteristics, thereby providing a reliable basis for the accurate determination of water supply dependency.

[0029] In the hydraulic model generation module, the process of constructing the water pipeline digital map is as follows: Fiber optic vibration signals are used to identify the characteristic vibration patterns of pipe fittings. Different pipe fittings produce unique vibration characteristics under the action of water flow: sudden changes in water flow direction at elbows cause periodic vortex shedding. The resulting vortex-induced vibration waveform exhibits specific frequency fluctuations, and the amplitude increases and decreases regularly with changes in water flow velocity. When valves are opened and closed, the rapid change in water flow conditions triggers a water hammer effect, whose wavefront characteristics are manifested as sudden increases and decreases in vibration amplitude, forming a steep waveform front, and the wavefront polarity differs significantly between closed and open positions. When a water pump is started, the synergistic effect of motor operation and water flow propulsion produces harmonics of specific frequencies. The frequencies of these harmonics are directly related to the pump power and speed, forming a recognizable characteristic spectrum. The system accurately identifies these characteristic vibration patterns by performing spectral analysis and waveform morphology comparison on the vibration signals collected by optical fibers, thereby distinguishing different types of pipe fittings.

[0030] After identifying characteristic vibration patterns, the system locates the pipe fittings based on the spatial distribution of these vibration signals. The continuous deployment of the fiber-optic sensor network ensures that each vibration signal corresponds to a specific physical coordinate. By matching the location information of the characteristic vibration patterns, the specific installation points of fittings such as elbows, valves, and pumps in the actual pipeline can be determined. For continuous pipeline sections, the system uses the time difference between the propagation of vibration waves within the pipeline to invert the actual length: the time interval for the vibration wave to propagate from one end of the section to the other, combined with the propagation characteristics of vibration waves in this type of pipeline, can be converted into the actual length of the pipeline, effectively correcting any dimensional deviations in the design drawings.

[0031] Finally, the system compares all identified pipe locations, pipe lengths, and other information with the original design drawings, completing missing details or correcting deviations, and generating a three-dimensional pipeline model with topological attributes. Topological attributes here refer to the consistency between the connection relationships between the various pipe fittings and pipe segments in the model and the actual pipe network, such as the connection angles between elbows and adjacent straight pipes, and the docking methods between valves and upstream and downstream pipes. The update cycle of the three-dimensional pipeline model is synchronized with the water supply dependency topology diagram to ensure that when the physical pipe network changes due to maintenance or renovation, the virtual model can promptly reflect these adjustments, providing accurate basic data for the subsequent construction of the hydraulic model.

[0032] The process of generating a dynamic hydraulic balance model by the hydraulic model generation module is to integrate the physical characteristics of the pipeline network with the real-time water usage status to construct a virtual model that can reflect the dynamic operation of the pipeline network.

[0033] This process uses a water supply dependency topology as its framework, which clearly demonstrates the hierarchical relationships and water supply directions of various water-using units. On this basis, the system overlays key physical information from a digital map of the water pipelines: pipe diameter change points mark the locations of sudden changes in the pipeline cross-section, directly affecting water flow velocity and pressure distribution; pump station locations are associated with the source of water supply power, and their operating status determines the pressure level of the pipeline network; and reservoir coordinates reflect the spatial distribution of water reserves, influencing the stability of water supply in local areas. This overlay of information imbues the model with the fundamental properties of a physical pipeline network, providing parameter support for the simulation of hydraulic conditions.

[0034] The next step in model construction is to assign initial weights to each node in the water dependency topology. These initial values ​​are determined based on the type of user associated with the node. For example, campus dormitories have a lower initial weight due to their regular daily water usage and relatively stable single-use consumption. On the other hand, workshops in campuses may have a higher initial weight due to the presence of high-flow equipment. This setting allows the model to initially match the water usage characteristics of different scenarios.

[0035] The system then calculates water use intensity by counting the number of water use event triggers per unit time at each node in real time and combining the waveform integral area corresponding to each trigger. The waveform integral area comprehensively reflects the flow rate and duration of the water use event. A larger integral area indicates a higher water use intensity. Water use intensity data is used to update node weight coefficients using a sliding time window. The length of the time window is set based on the frequency of changes in water use scenarios, ensuring that the weight coefficients promptly reflect recent changes in water use status.

[0036] When the rate of change of the weight coefficient of a node exceeds the threshold, the system will automatically mark it as an abnormal node, indicating that the node may have abnormal water use behavior or changes in the pipe network status. More importantly, the system will continuously monitor the weight coefficient ratio between adjacent level nodes: since the pipe diameter directly affects the water flow carrying capacity, under normal circumstances, the weight coefficient ratio of adjacent nodes should be consistent with the square of the pipe diameter ratio. This relationship reflects the inherent correlation between pipe diameter and flow. If the ratio continues to deviate, it means that the topology of the model may not match the actual water supply path. The system will trigger the topology verification process and re-check the dependencies between nodes to ensure that the dynamic hydraulic balance model can always accurately map the operating status of the physical pipe network.

[0037] In the intelligent water-saving control module, the process of generating a periodic intermittent shutdown instruction sequence is as follows: First, the weight coefficient change curves for the target node in the dynamic hydraulic balance model are obtained for several consecutive time periods. These curves record the fluctuations in water usage intensity of the node at different time periods. For example, campus dormitory nodes may show periodic differences between weekdays and weekends, while park workshop nodes may fluctuate regularly with changes in production shifts. The system analyzes the curve morphology to extract the stable and rising phases. The stable phase usually corresponds to a period of time when the node water usage intensity is stable, such as late at night when the dormitory area uses less water and the fluctuation is gentle. The rising phase indicates that water demand is about to increase, such as the gradual increase in water usage intensity before the morning rush hour. During the stable phase, the module generates a shutdown instruction. The duration of the shutdown instruction is determined by the target node's historical average water usage interval and a weight coefficient decay factor. The historical average water usage interval reflects the typical duration between two water use events at the node. For example, an office node experiences concentrated water use once every two hours on average. This interval provides a reference for the baseline duration of the shutdown instruction. The weight coefficient decay factor is dynamically adjusted based on the node's relative water use intensity, aligning the shutdown duration with the node's actual water conservation potential. Before the rising phase begins, the module inserts a pre-close command. This command briefly closes the valve before water demand increases, preventing ineffective water flow before peak periods. The duration of this command is negatively correlated with the slope of the weight coefficient. A steeper rise indicates a rapid increase in water demand, and the pre-close duration should be shortened to avoid impacting normal water use. A more gradual rise can increase the duration to maximize water conservation. For sibling nodes that rely on the same water supply source, the module employs a staggered shutdown strategy. The system sorts sibling nodes in ascending order by their weight coefficients, prioritizing nodes with lower weight coefficients for shutdown. In the generated staggered shutdown sequence, the time interval between shutdown commands for adjacent nodes is set to exceed the time required for water pressure fluctuations to stabilize. This is because shutting down valves at multiple nodes simultaneously can cause a sudden increase in water pressure in the local pipeline network, leading to pipeline vibration or equipment damage. Staggered control mitigates these pressure fluctuations by lag time, ensuring stable pipeline operation. The calculation of the weight coefficient attenuation factor is the key to achieving differentiated shutdown control. By dynamically adjusting the factor size, water-saving intervention can be more in line with the actual water use characteristics of the node. The module first establishes a correlation function between the target node's weight coefficient and the standard deviation of the weight coefficients of other nodes at the same level. The standard deviation reflects the overall dispersion of water use intensity among nodes at the same level: a small standard deviation indicates that the water use intensity of each node is relatively small and the overall state is relatively balanced; a large standard deviation indicates significant differentiation in water use intensity. When the standard deviation is less than the threshold, the system uses a fixed attenuation factor. In this case, nodes at the same level have similar water usage patterns, and a unified attenuation factor simplifies calculations while ensuring consistent control effects. For example, if the water intensity of nodes on the same floor of a residential complex varies little, a fixed factor can avoid overly complex adjustments. When the standard deviation exceeds the threshold, the attenuation factor is dynamically adjusted based on the target node's deviation from the average weight coefficient. If the target node's weight coefficient is lower than the average weight coefficient, it indicates low water intensity and significant potential for water conservation. In this case, increasing the attenuation factor will extend the shutdown duration to enhance water conservation. If the target node's weight coefficient is higher than the average weight coefficient, it indicates a relatively urgent water demand, requiring a lower attenuation factor and a shorter shutdown duration to ensure water availability.

[0038] Furthermore, the attenuation factor adjustment range is inversely proportional to the hierarchical depth from the target node to the root node in the water supply dependency topology. As the root node serves as the source of water supply, nodes with shallower hierarchical depths (such as main pipeline nodes close to the main water source) have a wider impact on the entire network, and the adjustment range needs to be narrowed to avoid global water pressure fluctuations. On the other hand, nodes with deeper hierarchical depths (such as terminal water users) have a more limited impact range, and the adjustment range can be appropriately increased to improve local water conservation efficiency. This hierarchical adjustment logic ensures water conservation while maintaining the overall stability of the network.

[0039] The present invention also includes a meteorological data fusion module. As a key component for the system to adapt to dynamic environmental changes, the meteorological data fusion module deeply couples meteorological factors with the pipe network hydraulic model to achieve environmental adaptability adjustment of the water-saving strategy. Specifically, it includes: First, a real-time data connection is established with regional meteorological stations to continuously collect three core meteorological parameters: rainfall intensity, evaporation, and sunshine duration. These parameters directly impact the actual water demand of the water-using system. Rainfall intensity reflects the natural water replenishment capacity. Higher rainfall intensity increases the natural wetness of the surface and vegetation, reducing the need for artificial irrigation. Evaporation and sunshine duration jointly determine the rate of water loss. Greater evaporation and more abundant sunshine lead to faster water loss from soil and water bodies, increasing water demand accordingly. The system performs time-series analysis on these parameters, constructs a correlation model based on historical data from the same period, and converts them into a regional water demand compensation coefficient. This coefficient is a quantitative indicator based on comprehensive meteorological conditions and is used to adjust the baseline water demand. When meteorological conditions are more humid (e.g., high rainfall and low evaporation), the coefficient decreases, indicating that actual water demand is below the baseline. When meteorological conditions are more arid (e.g., no rain and strong sunshine), the coefficient increases, indicating that water demand is above the baseline. When the regional water demand compensation coefficient remains below the threshold, indicating that actual water demand under current meteorological conditions is significantly lower than typical, the system adds a virtual water source node to the dynamic hydraulic balance model. A virtual water source node is not a physical water source, but rather a virtual regulating unit used to balance the model's supply and demand. Its weight coefficient is negatively correlated with the regional water demand compensation coefficient; the lower the compensation coefficient, the higher the virtual water source's weight. This setting enables the virtual water source to serve as a "substitute" in low-demand scenarios, reducing reliance on physical water sources. Furthermore, a bidirectional connection is established between the virtual water source node and the physical reservoir node. This connection is not a physical pipe connection, but a logical association at the model level that transmits supply and demand regulation signals. Once the connection takes effect, the system automatically triggers an intelligent valve opening priority reallocation strategy: for example, during periods of abundant rainfall, the priority of valves in irrigation areas is lowered, while the priority of valves in domestic water areas remains stable, ensuring that limited physical water resources prioritize core needs. The weight coefficient boost value of the virtual water source node is transmitted from top to bottom according to the hierarchical structure of the water supply dependency topology, forming a regulation gradient from source to terminal. During the transmission process, the boost value is equally attenuated at each node according to the number of out-degrees of the node. The out-degree of a node is the number of downstream nodes connected to the node. The higher the out-degree, the more downstream units the node needs to distribute the regulation signal. The equal attenuation can prevent the regulation force of a single node from excessively affecting the multi-level pipe network. For example, if the out-degree of the total water supply inlet node is high, its weight boost value will be evenly distributed according to the number of downstream nodes when it is transmitted to the next level, ensuring that each branch receives a reasonable regulation range. This transmission mechanism allows the influence of the virtual water source to gradually spread along the pipe network hierarchy, ensuring the integrity of the regulation while avoiding excessive regulation in local areas. The system continuously compares the actual water level sensor data of the physical reservoir node with the theoretical water level calculated by the virtual water source node. The theoretical water level is a predicted value derived from the virtual water source regulation, the water demand of the pipe network, and the physical water source replenishment capacity, while the actual water level reflects the actual water reserve status. When the deviation between the two exceeds the tolerance, it means that there is a significant difference between the model's prediction of the supply and demand relationship of the pipe network and the actual situation. This may be caused by hidden leaks in the pipe network, sensor errors, or topological structures that do not match the actual situation. At this time, the system automatically triggers the water supply dependency topology reconstruction process, re-checks the water supply dependency relationship of each node, corrects the pipe diameter parameters and water unit association information, so that the topology map more accurately reflects the current status of the physical pipe network, and provides a reliable model basis for the generation of subsequent water-saving strategies. By dynamically integrating meteorological data with hydraulic models, the system breaks away from the traditional water-saving strategies' reliance on fixed parameters. It can autonomously adjust its regulation logic based on environmental changes, ensuring water use stability while further improving water resource efficiency. This integration mechanism is particularly suitable for scenarios significantly affected by weather, such as campus landscaping and park irrigation, allowing water-saving control to better align with actual demand fluctuations.

[0040] The above is a detailed description of an embodiment of the present invention. However, the content described is only a preferred embodiment of the present invention and should not be considered to limit the scope of the present invention. All equivalent changes and improvements made within the scope of the present invention should still fall within the scope of the patent coverage of the present invention.

Claims

1. A digital twin intelligent water-saving system based on a distributed optical fiber sensing network, characterized in that: include: The distributed fiber optic sensing network consists of a single trunk fiber and multiple branch fibers forming a tree topology, and is laid continuously along the physical path of the water pipeline; The water use event recognition module is used to collect optical fiber vibration signals in real time and convert them into digital waveform sequences, and identify water use event trigger points by setting waveform amplitude thresholds; The water supply topology construction module is used to automatically construct a water supply dependency topology diagram between water-using units based on the spatial location of the water-using event trigger point and the time delay relationship between adjacent trigger points. The nodes in the topology diagram represent water-using units, and the directed edges in the topology diagram represent the water supply direction. A hydraulic model generation module is used to spatially superimpose the water supply dependency topology map with the preset water pipeline digital map to generate a dynamic hydraulic balance model, which includes a weight coefficient of the water use intensity of each node; The intelligent water-saving control module is used to send a periodic intermittent closing instruction sequence to the intelligent water valve associated with the low-weight coefficient node according to the real-time change trend of the node weight coefficient in the dynamic hydraulic balance model, when no physical leakage occurs. The duration of the instruction sequence is proportional to the difference in the weight coefficients of adjacent nodes.

2. The digital twin intelligent water-saving system based on a distributed optical fiber sensing network according to claim 1 is characterized in that: In the water supply topology construction module, the process of constructing the water supply dependency topology map is as follows: When a water use event trigger point is detected at the end of the branch optical fiber, the first vibration peak time of the water use event trigger point is recorded; if the vibration waveform similarity of the sensing point closest to the branch optical fiber end on the trunk optical fiber exceeds the threshold within the set time window, it is determined that the branch node depends on the trunk node for water supply; For branch nodes at the same level, if the triggering time interval between two branch nodes is less than the propagation time of the vibration wave in the pipeline, and the waveform envelope of the downstream branch node matches the attenuation shape of the upstream branch node, a directed edge is established from the upstream branch node to the downstream branch node. After all dependencies are determined, the node groups with the same water supply source are merged to form a hierarchical topology. The top node of the hierarchical topology is the main water supply entrance of the park, and the bottom node of the hierarchical topology is the terminal water use unit.

3. The digital twin intelligent water-saving system based on a distributed optical fiber sensing network according to claim 2 is characterized in that: The method for determining the vibration waveform similarity is: The original vibration waveform of a fixed time length before and after the trigger point of the branch node is intercepted as the sequence to be matched, and the vibration waveform of the corresponding time window of the candidate trunk fiber node is simultaneously intercepted as the reference sequence; the length of the time window is calculated by dividing the physical distance between the branch fiber and the trunk fiber by the water hammer wave velocity under the pipe diameter; The sequence to be matched and the reference sequence are aligned nonlinearly along the time axis, and the minimum cumulative distance on the alignment path is calculated. When the minimum cumulative distance is less than the reference value of the sound wave propagation loss determined by the pipeline material, the waveform similarity is determined to meet the standard.

4. The digital twin intelligent water-saving system based on a distributed optical fiber sensing network according to claim 1 is characterized in that: In the hydraulic model generation module, the process of constructing the water pipeline digital map is as follows: Identify characteristic vibration modes of pipe fittings through optical fiber vibration signals. These include vortex-induced vibration waveforms at elbows, water hammer wavefront characteristics during valve opening and closing, and specific frequency harmonics during pump startup. The position of pipe fittings is located according to the spatial distribution of characteristic vibration modes; the actual length of the pipeline section is inverted using the time difference of vibration wave propagation in continuous pipeline sections; and a three-dimensional pipeline model with topological attributes is generated after comparing the identification results with the design drawings. The update cycle of the three-dimensional pipeline model is synchronized with the water supply dependency topology map.

5. The digital twin intelligent water-saving system based on a distributed optical fiber sensing network according to claim 4 is characterized in that: In the hydraulic model generation module, the process of generating a dynamic hydraulic balance model is as follows: Based on the water supply dependency topology map, the pipe diameter change points, pump station locations, and reservoir coordinate information in the digital map of the water pipeline are superimposed; Assign an initial weight coefficient to each node in the water supply dependency topology graph. The initial weight coefficient value is determined by the water use unit type associated with the node. The number of water use event triggering per unit time at each node is counted in real time, and the water use intensity is calculated based on the waveform integral area corresponding to each water use event triggering. The water use intensity data updates the node weight coefficient in a sliding time window manner, and nodes whose weight coefficient change rate exceeds the threshold are automatically marked as abnormal nodes. When the weight coefficient ratio between adjacent level nodes continuously deviates from the square of the pipe diameter ratio, the topology structure verification process is triggered.

6. The digital twin intelligent water-saving system based on a distributed optical fiber sensing network according to claim 1 is characterized in that: In the intelligent water-saving control module, the process of generating a periodic intermittent shutdown instruction sequence is as follows: Obtain the weight coefficient change curve of the target node in the dynamic hydraulic balance model for several consecutive time periods, and extract the stable stage and rising stage in the weight coefficient change curve; Generate a shutdown instruction in the stable phase, and the duration of the shutdown instruction is equal to the historical average water consumption interval of the target node multiplied by the weight coefficient attenuation factor; Insert a pre-closing instruction before the rising phase, and the duration of the pre-closing instruction is negatively correlated with the rising slope of the weight coefficient; For brother nodes that rely on the same water supply source, a staggered shutdown schedule is generated after the brother nodes are arranged in ascending order according to their weight coefficients. The start-up time interval of the shutdown instructions of adjacent nodes in the staggered shutdown schedule is greater than the time required for the water pressure fluctuation to stabilize.

7. The digital twin intelligent water-saving system based on a distributed optical fiber sensing network according to claim 6 is characterized in that: The weight coefficient attenuation factor is calculated as follows: Establish a correlation function between the target node weight coefficient and the standard deviation of the weight coefficients of other nodes at the same level. When the standard deviation is less than the threshold, a fixed attenuation factor is used. When the standard deviation is greater than the threshold, the attenuation factor is dynamically adjusted according to the degree of deviation between the target node and the average weight coefficient. That is, when the target node weight coefficient is lower than the average weight coefficient, the attenuation factor is increased, and when the target node weight coefficient is higher than the average weight coefficient, the attenuation factor is reduced. The adjustment amplitude of the attenuation factor is inversely proportional to the hierarchical depth from the target node to the root node in the water supply dependency topology graph.

8. The digital twin intelligent water-saving system based on a distributed optical fiber sensing network according to claim 1 is characterized in that: It also includes meteorological data fusion modules, specifically: Real-time access to rainfall intensity, evaporation, and sunshine duration data from regional meteorological stations, converting rainfall intensity, evaporation, and sunshine duration data into regional water demand compensation coefficients; When the regional water demand compensation coefficient continues to be lower than the threshold, a virtual water source node is added to the dynamic hydraulic balance model. The weight coefficient of the virtual water source node is negatively correlated with the regional water demand compensation coefficient. A bidirectional connection edge is established between the virtual water source node and the physical reservoir node, triggering the intelligent water valve opening priority redistribution strategy.

9. The digital twin intelligent water-saving system based on a distributed optical fiber sensing network according to claim 8, characterized in that: The functions of the virtual water source node are: When the regional water demand compensation coefficient decreases, the virtual water source node automatically increases its weight coefficient value. The weight coefficient increase value is transmitted from top to bottom according to the hierarchical structure of the water supply dependency topology graph. During the transmission process, each time a node in the water supply dependency topology graph is passed, the weight coefficient increase value is attenuated in equal parts according to the number of node out-degrees. When the deviation between the actual water level sensor data of the physical reservoir node and the theoretical water level calculated by the virtual water source node exceeds the tolerance, the water supply dependency topology reconstruction process is triggered.

Images