Intelligent water valve cooperative optimization method and device for building scene

Abstract

The application provides a kind of intelligent water valve cooperative optimization method and device for building scene, the method comprises: obtaining the target topology graph of target building pipe network;According to the target topology graph, determine a second intelligent water valve node;Acquire local state information and a neighbor state information;Based on local cost function and constraint condition, according to local state information and a neighbor state information, the predicted state information and target hydraulic impedance sequence are obtained by solving;According to the target hydraulic impedance sequence, determine the valve opening instruction, drive the valve mechanical component according to the valve opening instruction in the next control cycle;The predicted state information is broadcast to a second intelligent water valve node, to cooperatively adjust the pressure distribution of target building pipe network.Through topology self-discovery mechanism and multi-valve cooperative control mechanism, the intelligent level and self-adaptive ability of hydraulic balance regulation and control in building scene can be improved.

Description

Technical Field

[0001] This application relates to the field of intelligent water valve control technology, and in particular to an intelligent water valve collaborative optimization method and device for building scenarios. Background Technology

[0002] In high-rise building water supply networks, due to differences in static pressure caused by variations in floor height and random changes in user water load, the actual water supply pressure on each floor often deviates from the design value. Excessive pressure on lower floors can easily cause pipe noise and water hammer, while insufficient pressure on higher floors can lead to problems such as low water flow and water heaters failing to start. Traditional solutions rely on mechanical balancing valves or differential pressure regulating valves, which are manually set once based on the design flow rate. This cannot adapt to real-time fluctuations in water usage conditions, and the debugging process is time-consuming, labor-intensive, and difficult to guarantee accuracy. For large and complex building water supply networks, it is almost impossible to achieve globally optimal hydraulic balance regulation.

[0003] Current IoT smart valve solutions require uploading sensor data to a central controller via wired or wireless means for global optimization calculations before issuing control commands to each valve. This centralized control architecture places extremely high demands on the computing power and communication reliability of the central node; if the central node fails, the entire system collapses, resulting in poor system robustness and scalability.

[0004] Therefore, it is urgent to address how to improve the intelligence and adaptability of hydraulic balance control in building scenarios. Summary of the Invention

[0005] This application provides a method and apparatus for intelligent water valve collaborative optimization in building scenarios. Through a topology self-discovery mechanism and a multi-valve collaborative control mechanism, it improves the intelligence level and adaptability of hydraulic balance control in building scenarios.

[0006] In a first aspect, embodiments of this application provide a method for intelligent water valve collaborative optimization in a building scenario, applied to a first intelligent water valve node in an intelligent water valve collaborative control system. The intelligent water valve collaborative control system includes N intelligent water valve nodes, which are distributed and installed in the target building's pipe network, where N is an integer greater than 1. The first intelligent water valve node is any one of the N intelligent water valve nodes. The first intelligent water valve node is configured with valve mechanical components and a wireless communication module. The method includes: Obtain the target topology map of the target building's pipe network; the target topology map is used to characterize the physical pipe connection relationships between each smart water valve node in the target building's pipe network; Based on the target topology graph, determine the neighboring nodes of the first smart water valve node to obtain a second smart water valve nodes; a is a positive integer less than or equal to 2. Based on a preset control cycle, the local status information of the first smart water valve node is obtained, and the status information of the a neighbors corresponding to the a second smart water valve nodes is obtained through the wireless communication module. Based on the preset local cost function and constraints, the predicted state information and the target hydraulic impedance sequence are obtained by solving the problem according to the local state information and the state information of the a neighbors. The valve opening command is determined based on the target hydraulic impedance sequence, and the valve mechanical components are driven according to the valve opening command in the next control cycle. The predicted state information is broadcast to the a second intelligent water valve nodes via the wireless communication module to coordinate the pressure distribution of the target building's pipe network.

[0007] Secondly, this application provides an intelligent water valve collaborative optimization device for building scenarios, applied to a first intelligent water valve node in an intelligent water valve collaborative control system. The intelligent water valve collaborative control system includes N intelligent water valve nodes, which are distributed and installed in the target building's pipe network, where N is an integer greater than 1. The first intelligent water valve node is any one of the N intelligent water valve nodes. The first intelligent water valve node is configured with valve mechanical components and a wireless communication module. The device includes a first acquisition module, a first determination module, a second acquisition module, a processing module, a second determination module, and a broadcast module, wherein: The first acquisition module is used to acquire a target topology map of the target building's pipe network; the target topology map is used to characterize the physical pipe connection relationship between each smart water valve node in the target building's pipe network; The first determining module is used to determine the neighboring nodes of the first smart water valve node according to the target topology map, and obtain a second smart water valve nodes; a is a positive integer less than or equal to 2; The second acquisition module is used to acquire the local status information of the first smart water valve node based on a preset control cycle, and to acquire the status information of a neighbors corresponding to the a second smart water valve nodes through the wireless communication module. The processing module is used to solve the local state information and the state information of the a neighboring states based on a preset local cost function and constraints to obtain the predicted state information and the target hydraulic impedance sequence. The second determining module is used to determine the valve opening command based on the target hydraulic impedance sequence, and drive the valve mechanical components according to the valve opening command in the next control cycle; The broadcast module is used to broadcast the predicted state information to the a second smart water valve nodes through the wireless communication module in order to coordinate the pressure distribution of the target building pipe network.

[0008] Thirdly, embodiments of this application provide an electronic device, including a processor, a memory, a communication interface, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the processor, and the programs include instructions for performing steps in any method of the first aspect of this application.

[0009] Fourthly, embodiments of this application provide a computer-readable storage medium storing a computer program for electronic data interchange, wherein the computer program causes a computer to perform some or all of the steps described in any method of the first aspect of this application.

[0010] Fifthly, embodiments of this application provide a computer program product, wherein the computer program product includes a non-transitory computer-readable storage medium storing a computer program operable to cause a computer to perform some or all of the steps described in any method of the first aspect of this application. The computer program product may be a software installation package.

[0011] By implementing the embodiments of this application, without relying on a central controller, each smart water valve node exchanges status and prediction information only with its physically connected neighbor nodes, and performs distributed collaborative control in parallel and asynchronously. This achieves adaptive equilibrium of building pipeline pressure distribution and solves the problems of strong dependence on manual debugging and poor robustness of centralized architecture. Attached Figure Description

[0012] To more clearly illustrate the technical solutions of the embodiments of this application, the drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0013] Figure 1 This is a system architecture diagram of an intelligent water valve collaborative control system provided in an embodiment of this application; Figure 2 This is a schematic diagram illustrating the composition of a first intelligent water valve node provided in an embodiment of this application; Figure 3 This is a schematic diagram illustrating the composition of a cloud management platform provided in an embodiment of this application; Figure 4 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application; Figure 5 This is a flowchart illustrating a method for collaborative optimization of intelligent water valves in a building setting, as provided in an embodiment of this application. Figure 6 This is a flowchart illustrating a distributed model predictive control solution method provided in an embodiment of this application; Figure 7 This is a flowchart illustrating a method for determining a valve opening command, as provided in an embodiment of this application. Figure 8 This is a functional module block diagram of an intelligent water valve collaborative optimization device for building scenarios provided in this application embodiment. Detailed Implementation

[0014] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present application.

[0015] The terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish different objects, not to describe a specific order. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or apparatus that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to these processes, methods, products, or apparatuses.

[0016] It should be understood that the term "and / or" in this document is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. Additionally, the character " / " in this document indicates that the preceding and following related objects are in an "or" relationship. In the embodiments of this application, "multiple" refers to two or more.

[0017] In the embodiments of this application, "at least one item" or its similar expression refers to any combination of these items, including any combination of a single item or a plurality of items. "One or more" means one or more, while "multiple" means two or more. For example, "at least one item" of a, b, or c can represent the following seven cases: a, b, c; a and b; a and c; b and c; a, b, and c. Each of a, b, and c can be an element or a set containing one or more elements.

[0018] In this application, the term "connection" refers to various connection methods, such as direct connection or indirect connection, to achieve communication between devices. This application does not impose any limitations on this.

[0019] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0020] In high-rise building water supply networks, due to differences in static pressure caused by variations in floor height and random changes in user water load, the actual water supply pressure on each floor often deviates from the design value. Excessive pressure on lower floors can easily cause pipe noise and water hammer, while insufficient pressure on higher floors can lead to problems such as low water flow and water heaters failing to start. Traditional solutions rely on mechanical balancing valves or differential pressure regulating valves, which are manually set once based on the design flow rate. This cannot adapt to real-time fluctuations in water usage conditions, and the debugging process is time-consuming, labor-intensive, and difficult to guarantee accuracy. For large and complex building water supply networks, it is almost impossible to achieve globally optimal hydraulic balance regulation.

[0021] Current IoT smart valve solutions require uploading sensor data to a central controller via wired or wireless means for global optimization calculations before issuing control commands to each valve. This centralized control architecture places extremely high demands on the computing power and communication reliability of the central node; if the central node fails, the entire system collapses, resulting in poor system robustness and scalability.

[0022] Therefore, it is urgent to address how to improve the intelligence and adaptability of hydraulic balance control in building scenarios.

[0023] To address the aforementioned issues, this application provides a method and apparatus for intelligent water valve collaborative optimization in building scenarios. The method and apparatus are applied to a first intelligent water valve node in an intelligent water valve collaborative control system. The intelligent water valve collaborative control system comprises N intelligent water valve nodes, which are distributed and installed in the target building's pipe network, where N is an integer greater than 1. The first intelligent water valve node is any one of the N intelligent water valve nodes. The first intelligent water valve node is equipped with valve mechanical components and a wireless communication module. First, a target topology map of the target building's pipe network is obtained. This target topology map represents the physical pipe connections between each smart water valve node in the target building's pipe network. Then, based on the target topology map, the neighbor nodes of the first smart water valve node are determined, resulting in *a* second smart water valve nodes, where *a* is a positive integer less than or equal to 2. Next, based on a preset control cycle, the local state information of the first smart water valve node is obtained, and the state information of *a* neighbor nodes corresponding to the *a* second smart water valve nodes is obtained through the wireless communication module. Based on a preset local cost function and constraints, the predicted state information and the *a* neighbor state information are solved to obtain the predicted state information and the target hydraulic impedance sequence. Then, the valve opening command is determined based on the target hydraulic impedance sequence, and the valve mechanical components are driven according to the valve opening command in the next control cycle. Finally, the predicted state information is broadcast to the *a* second smart water valve nodes through the wireless communication module to coordinate the adjustment of the pressure distribution of the target building's pipe network.

[0024] It is evident that the topology self-discovery mechanism and multi-valve collaborative control mechanism have improved the intelligence level and adaptability of hydraulic balance control in building scenarios.

[0025] For easier understanding, please refer to Figure 1 , Figure 1 This is a system architecture diagram of an intelligent water valve collaborative control system provided in an embodiment of this application. The intelligent water valve collaborative control system includes N intelligent water valve nodes and a cloud management platform. The N intelligent water valve nodes are distributed and installed on the pipes of each floor of the target building's pipe network. The cloud management platform communicates with each intelligent water valve node via a wireless network to distribute configuration parameters (such as desired pressure, pressure limits, impedance range, etc.) and receive operating status and topology information reported by each node. The intelligent water valve nodes communicate with each other through wireless communication modules via point-to-point or broadcast communication, exchanging real-time status information and predicted status information to achieve decentralized distributed collaborative control.

[0026] For easier understanding, please refer to Figure 2 , Figure 2This is a schematic diagram illustrating the composition of a first intelligent water valve node according to an embodiment of this application. The first intelligent water valve node includes a local controller, a wireless communication module, a pressure sensor, a flow sensor, valve mechanical components, a sound wave transmitter, a sound wave receiver, and a power supply module. The local controller is electrically connected to the wireless communication module, pressure sensor, flow sensor, valve mechanical components, sound wave transmitter, and sound wave receiver, and is used to execute algorithms related to topology self-discovery and cooperative control. The pressure sensor is installed on the outlet side of the valve pipe to measure the downstream pressure in real time. The flow sensor is installed inside the valve or in an adjacent pipe to measure the instantaneous flow rate through the valve in real time. The sound wave transmitter is used to transmit specifically coded low-frequency pressure pulses into the pipe. The sound wave receiver is used to detect pressure pulses from other nodes in the pipe. The wireless communication module is used to exchange data with other intelligent water valve nodes and the cloud management platform. The valve mechanical components include a drive motor and a valve body, used to adjust the valve opening according to the instructions of the local controller. The power supply module supplies power to all the above components.

[0027] For easier understanding, please refer to Figure 3 , Figure 3 This is a schematic diagram illustrating the composition of a cloud management platform provided in an embodiment of this application. The cloud management platform includes: a configuration management unit, a topology management unit, a status monitoring unit, a storage unit, and a communication unit. The configuration management unit is used to distribute collaborative control parameters to each intelligent water valve node. These collaborative control parameters include the desired pressure, pressure limit, hydraulic impedance range constraints, and weighting coefficients for each node. The topology management unit is used to receive and visualize the target topology map reported by each intelligent water valve node, presenting the physical pipeline connection relationships between nodes and neighbor node information. The status monitoring unit is used to receive real-time operating status data reported by each intelligent water valve node, including real-time pressure, real-time flow, current valve opening, and estimated hydraulic impedance, and provides anomaly alarm functions. The storage unit is used to store basic building parameters of the building's pipe network, historical operating data of each node, and system configuration information. The communication unit is used to conduct bidirectional data communication with each intelligent water valve node via a wireless network, enabling the distribution of configuration parameters and the reception of operating data.

[0028] The following is combined with Figure 4 The electronic devices in the embodiments of this application will be described. Figure 4 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application, such as... Figure 4 As shown, the electronic device includes one or more processors, a memory, a communication interface, and one or more programs. The processor is connected to the memory and the communication interface via an internal communication bus.

[0029] The processor can be used for: Obtain the target topology map of the target building's pipe network; the target topology map is used to characterize the physical pipe connection relationships between each smart water valve node in the target building's pipe network; Based on the target topology graph, determine the neighboring nodes of the first smart water valve node, and obtain a second smart water valve nodes; a is a positive integer less than or equal to 2; Based on a preset control cycle, the local status information of the first smart water valve node is obtained, and the status information of a neighboring nodes corresponding to a second smart water valve nodes is obtained through the wireless communication module. Based on the preset local cost function and constraints, the solution is obtained by solving the local state information and the state information of a neighboring states, thus obtaining the predicted state information and the target hydraulic impedance sequence. The valve opening command is determined based on the target hydraulic impedance sequence, and the valve mechanical components are driven according to the valve opening command in the next control cycle. The predicted status information is broadcast to a second intelligent water valve node via a wireless communication module to coordinate the adjustment of the pressure distribution of the target building's pipe network.

[0030] The one or more programs are stored in the aforementioned memory and configured to be executed by the aforementioned processor, and the one or more programs include instructions for performing any step in the above method embodiments.

[0031] The processor can be a central processing unit (CPU), a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. It can implement or execute the various exemplary logic blocks, cells, and circuits described in conjunction with the disclosure of this application. The processor can also be a combination that implements computational functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, etc. The communication unit can be a communication interface, transceiver, transceiver circuit, etc., and the storage unit can be a memory.

[0032] The memory can be volatile or non-volatile, or a combination of both. Non-volatile memory can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. Volatile memory can be random access memory (RAM), used as an external cache. By way of example, but not limitation, many forms of random access memory (RAM) are available, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate synchronous DRAM (DDR SDRAM), enhanced synchronous DRAM (ESDRAM), synchronous linked DRAM (SLDRAM), and direct rambus RAM (DR RAM).

[0033] It is understood that the electronic device may include more or fewer structural elements than those shown in the block diagram above, such as a power module, physical buttons, a Wi-Fi module, a speaker, a Bluetooth module, sensors, a display module, etc., without limitation. It is understood that the electronic device may be as follows: Figure 2 The first intelligent water valve node.

[0034] After understanding the software and hardware architecture of this application, the following will be combined with... Figure 5 This application describes a method for intelligent water valve collaborative optimization in a building scenario. Figure 5 This is a flowchart illustrating a smart water valve collaborative optimization method for a building scenario, provided in an embodiment of this application. It is applied to a first smart water valve node in a smart water valve collaborative control system. The smart water valve collaborative control system includes N smart water valve nodes, which are distributed and installed in the target building's pipe network, where N is an integer greater than 1. The first smart water valve node is any one of the N smart water valve nodes. The first smart water valve node is configured with valve mechanical components and a wireless communication module, and specifically includes the following steps: Step S501: Obtain the target topology map of the target building's pipeline network.

[0035] The target topology map is used to characterize the physical pipe connection relationships between each smart water valve node in the target building pipe network.

[0036] The first intelligent water valve node is also equipped with a pressure sensor. Before acquiring the target topology map of the target building's pipe network, the method further includes the following steps: S11. Receive neighbor discovery requests broadcast by b second smart water valve nodes through the wireless communication module to obtain b neighbor discovery requests; the b second smart water valve nodes are all neighboring nodes of the first smart water valve node among N-1 smart water valve nodes; b is an integer greater than or equal to a and less than N-1. S12. Obtain the b node identifiers and b pulse codes carried in the b neighbor discovery requests; S13. Determine the b reception times and b wireless signal strengths corresponding to the b neighbor discovery requests; S14. Based on the b pulse codes, the pressure fluctuations in the pipes of the target building's pipe network are matched and detected by the pressure sensor to obtain b pressure pulses; the b pressure pulses correspond one-to-one with the b pulse codes; S15. Determine the b arrival times corresponding to the b pressure pulses; S16. Determine b propagation times based on the b reception times and the b arrival times; S17. Determine b hydraulic distances in the pipeline based on the preset pulse propagation speed and the b propagation times; the hydraulic distance in the pipeline represents the actual physical path length of the pressure pulse propagating inside a water-filled pipeline. S18. Based on the strength of the b wireless signals and the hydraulic distance of the b pipelines, the b second smart water valve nodes are filtered to obtain the a second smart water valve nodes; the a second smart water valve nodes are used to construct the target topology map.

[0037] In a specific embodiment, during the initialization phase of the intelligent water valve collaborative control system, each intelligent water valve node needs to automatically construct the target topology map of the target building's pipe network. Specifically, the self-discovery process of the topology is explained in detail for the first intelligent water valve node. First, the first intelligent water valve node listens for neighbor discovery requests broadcast by other intelligent water valve nodes through its own wireless communication module. Since the first intelligent water valve node also broadcasts its own neighbor discovery requests, other intelligent water valve nodes will perform the same listening and detection operations. Within the wireless communication coverage area, the first intelligent water valve node will receive b neighbor discovery requests sent by neighboring intelligent water valve nodes (i.e., the second intelligent water valve node). The value of b depends on the wireless communication coverage area and the actual deployment density; its value is greater than or equal to the final determined number of real physical neighbors, a, and less than the total number of nodes in the system, N-1, excluding the first intelligent water valve node. Each neighbor discovery request is transmitted almost in real time in the form of radio electromagnetic waves, and its propagation time is negligible.

[0038] Then, for each of the b received neighbor discovery requests, the first smart water valve node parses out the node identifier and pulse code carried in the request. The node identifier uniquely identifies the signal source, and the pulse code defines the specific physical characteristics of the low-frequency pressure pulse (i.e., acoustic pressure pulse) that the neighbor node will soon transmit into the pipe via the acoustic transmitter. This pulse code can be a sequence with good autocorrelation properties, such as a Barker code or a linear frequency modulation (LFM) signal pattern, used to accurately identify valid signals in complex pipe background noise; no specific limitations are imposed here.

[0039] Next, the first smart water valve node records the reception time of each of the b neighbor discovery requests and simultaneously measures the wireless signal strength (such as RSSI value) at the time of receiving the request, thus obtaining b reception times and b wireless signal strengths. Since the reception time of the wireless signal can be regarded as the synchronization reference for the transmission of the acoustic pulse, the first smart water valve node then uses this reception time as the starting point to start a high-precision timer and continuously monitors the pressure fluctuations in the pipeline through a pressure sensor.

[0040] Then, the first intelligent water valve node uses the b pulse codes to perform matching detection on the pressure fluctuation signals in the pipeline collected by the pressure sensor. Specifically, each pulse code can be used as a template for a matched filter and subjected to sliding cross-correlation with the received pressure fluctuation signal. When the waveform of the pressure fluctuation in the pipeline matches a preset pulse code, the correlation operation will output a sharp correlation peak. The time corresponding to this peak is the arrival time of the pressure pulse. In this way, the first intelligent water valve node can detect b pressure pulses corresponding one-to-one with the b pulse codes from complex environmental noise and multipath reflection signals in the pipeline, and record their respective arrival times, i.e., the b arrival times.

[0041] Next, for each matched neighbor node, the first smart water valve node calculates the difference between the neighbor node's reception time and propagation time to obtain the propagation time of the pressure pulse within the pipe. Then, based on a preset pulse propagation speed (i.e., the propagation speed of the pressure pulse in water, approximately 1430 m / s, the specific value can be corrected online according to water temperature), the first smart water valve node multiplies this propagation time by the pulse propagation speed to calculate the hydraulic distance between the first smart water valve node and the neighbor node. The hydraulic distance represents the actual physical path length of the pressure pulse propagating from one node to another within a water-filled pipe, rather than the straight-line distance in space. Finally, based on b wireless signal strengths and b hydraulic distances, b second smart water valve nodes are selected to obtain a second smart water valve nodes, which are used to construct the target topology map.

[0042] It is evident that by combining wireless and acoustic ranging with dual-criteria filtering, each smart water valve node can automatically and accurately identify physically connected neighbor nodes and construct the target building's pipeline topology without requiring manual configuration.

[0043] The step of filtering the b second smart water valve nodes based on the b wireless signal strengths and the b hydraulic distances in the pipelines to obtain the a second smart water valve nodes includes the following specific steps: S21. Obtain the length of the vertical main pipe and the length of the horizontal branch pipe corresponding to the target building's pipe network; the length of the vertical main pipe is the length of the vertical pipe segment connecting two adjacent smart water valve nodes; the length of the horizontal branch pipe is the length of the horizontal pipe segment from the main pipe branch interface to the smart water valve node on each floor. S22. Determine the reference pipeline hydraulic distance based on the length of the vertical main pipe and the length of the horizontal branch pipe; S23. Determine the hydraulic distance range of the pipeline based on the preset reference ratio and the reference pipeline hydraulic distance; S24. The b second intelligent water valve nodes are filtered according to the reference filtering conditions to obtain the a second intelligent water valve nodes; the reference filtering conditions are that the hydraulic distance of the pipeline is within the hydraulic distance range of the pipeline and the wireless signal strength is greater than the preset signal strength threshold.

[0044] In a specific embodiment, the first intelligent water valve node first acquires the lengths of the vertical main pipe and horizontal branch pipe corresponding to the target building's pipe network. The vertical main pipe length refers to the length of the vertical pipe segment connecting two adjacent intelligent water valve nodes, and its value is usually directly related to the floor height of the building. For example, if the standard floor height is 3 meters and the riser is laid vertically along the pipe shaft, the vertical main pipe length between the valves on the upper and lower floors is approximately 3 meters. The horizontal branch pipe length refers to the length of the horizontal pipe segment from the main pipe branch interface to the installation position of the intelligent water valve node on each floor. In actual engineering, the length of the horizontal branch pipe is usually shorter; for example, it may extend from the riser tee in the pipe shaft to the valve installation position in the bathroom or equipment room, and this segment length is generally between 0.5 meters and 2 meters. The lengths of the vertical main pipe and horizontal branch pipe can be building structure parameters pre-stored in the local memory of the first intelligent water valve node, or they can be uniformly distributed by the cloud management platform during the initialization phase.

[0045] Next, the first intelligent water valve node determines the reference hydraulic distance based on the obtained vertical main pipe length and horizontal branch pipe length. Specifically, for two adjacent intelligent water valve nodes installed in a riser series structure, the actual pipe path traversed by the pressure pulse from the upstream node to the downstream node consists of three pipe segments: the horizontal branch pipe of the upstream node, the vertical main pipe connecting the upper and lower layers, and the horizontal branch pipe of the downstream node. Therefore, the reference hydraulic distance is calculated by adding the vertical main pipe length to twice the horizontal branch pipe length.

[0046] Then, the first intelligent water valve node determines the hydraulic distance range of the pipeline based on a preset reference ratio and a reference pipeline hydraulic distance. Due to potential bends or detours in the pipeline's route during actual construction, and the slight influence of factors such as pipeline material and water temperature on the speed of sound, there is a certain engineering deviation between the actual pipeline hydraulic distance and the reference pipeline hydraulic distance. Therefore, a preset reference ratio can be used as a floating range, for example, ±30%. Specifically, the reference pipeline hydraulic distance is multiplied by the first ratio (i.e., 1 - reference ratio) as the lower limit of the pipeline hydraulic distance range, and the reference pipeline hydraulic distance is multiplied by the second ratio (i.e., 1 + reference ratio) as the upper limit of the pipeline hydraulic distance range. For example, if the reference pipeline hydraulic distance is 4 meters and the reference ratio is set to 30%, then the pipeline hydraulic distance range is [2.8 meters, 5.2 meters]. Only nodes whose actual measured pipeline hydraulic distance falls within this range are considered potential direct neighbors between upper and lower floors; nodes on the same floor with excessively small distances or nodes on adjacent floors with excessively large distances will be excluded.

[0047] Finally, b second smart water valve nodes are filtered according to reference screening criteria to obtain a second smart water valve nodes, which are the a neighbor nodes of the first smart water valve node. The reference screening criteria are that the hydraulic distance to the pipeline is within the specified hydraulic distance range, and the wireless signal strength is greater than a preset signal strength threshold.

[0048] It is evident that by dynamically determining the hydraulic distance range of the pipeline by combining building structural parameters, the accuracy of neighbor node selection is effectively improved.

[0049] Step S502: Determine the neighboring nodes of the first smart water valve node according to the target topology map to obtain a second smart water valve nodes.

[0050] Where 'a' is a positive integer less than or equal to 2, after the first smart water valve node completes topology self-discovery and constructs the target topology map, this target topology map is stored in the local controller in the form of a data structure, used to represent the physical pipe connection relationships between each smart water valve node in the target building's pipe network. The first smart water valve node can query this target topology map to retrieve all other smart water valve nodes that have a direct physical pipe connection relationship with itself, and determine these smart water valve nodes as its own neighbor nodes, i.e., 'a' second smart water valve nodes.

[0051] Step S503: Based on a preset control cycle, obtain the local status information of the first smart water valve node, and obtain the status information of a neighbors corresponding to the a second smart water valve nodes through the wireless communication module.

[0052] Specifically, the first intelligent water valve node triggers coordinated control operations at preset control intervals (e.g., T=1 second). At the beginning of each control cycle, the first intelligent water valve node first collects the real-time pressure and instantaneous flow rate at the current moment through its configured pressure and flow sensors, forming local status information. This local status information includes the first real-time pressure and the first instantaneous flow rate of the first intelligent water valve node. Then, it receives the status information of a neighbors broadcast by a second intelligent water valve nodes at the end of the previous control cycle via a wireless communication module.

[0053] Step S504: Based on the preset local cost function and constraints, solve the problem according to the local state information and the state information of the a neighbors to obtain the predicted state information and the target hydraulic impedance sequence.

[0054] The steps of solving the problem based on a preset local cost function and constraints, using the local state information and the state information of a neighboring states to obtain the predicted state information and the target hydraulic impedance sequence, specifically include: S31. Obtain the first real-time pressure and the first instantaneous flow rate from the local status information; S32. Obtain a second real-time pressure, a second instantaneous flow rate, and a neighbor predicted pressure sequence from the a neighbor status information; the a neighbor predicted pressure sequence is the predicted pressure data in the prediction time domain generated and broadcast by the a second smart water valve nodes in the previous control cycle; the prediction time domain includes c control cycles; c is a positive integer less than or equal to 3; S33. Based on the target topology map, determine the upstream neighbor node of the first smart water valve node from the a second smart water valve nodes; S34. Determine the current pressure drop based on the second real-time pressure corresponding to the upstream neighbor node in the a second real-time pressure and the first real-time pressure; S35. Based on the current pressure drop and the first instantaneous flow rate, estimate the current local hydraulic impedance according to the preset pipeline hydraulic state equation; S36. Obtain the first desired pressure and the historical instantaneous flow rate of the first intelligent water valve node in the previous control cycle; S37. Determine a first parameter set based on the current local hydraulic impedance, the first real-time pressure, the first instantaneous flow rate, the first expected pressure, the historical instantaneous flow rate, the a second real-time pressures, and the a neighbor predicted pressure sequences; S38. Based on the local cost function and the constraint conditions, determine the predicted state information and the target hydraulic impedance sequence according to the first parameter set.

[0055] In a specific embodiment, firstly, the first intelligent water valve node extracts the first real-time pressure and the first instantaneous flow rate from its local state information. The first real-time pressure refers to the downstream pressure value measured by the first intelligent water valve node through a pressure sensor at the current moment, and the first instantaneous flow rate refers to the instantaneous flow rate through the valve measured by the first intelligent water valve node through a flow sensor at the current moment. Then, the first intelligent water valve node parses a second real-time pressure, a second instantaneous flow rate, and a neighbor predicted pressure sequences from the received a neighbor state information. Each second real-time pressure is the real-time pressure measurement value of the corresponding second intelligent water valve node at the current moment, and each second instantaneous flow rate is the real-time flow measurement value of the corresponding second intelligent water valve node. Each neighbor predicted pressure sequence is a set of predicted pressure data in the prediction time domain generated and broadcast by the corresponding second intelligent water valve node after completing the distributed model predictive control solution in the previous control cycle. This predicted pressure sequence contains the predicted pressure values ​​for each future control cycle in the prediction time domain, and the prediction time domain contains c control cycles, where c is a positive integer less than or equal to 3, preferably c=2 or c=3.

[0056] Then, the first smart water valve node can determine its upstream neighbor node from among the *a* second smart water valve nodes based on the target topology. The current pressure drop is obtained by subtracting the first real-time pressure of the first smart water valve node from the second real-time pressure of the upstream neighbor node. This current pressure drop characterizes the pressure loss caused by the local resistance of the valve when water flows from the upstream neighbor node through the valve of the first smart water valve node. It should be noted that if the first smart water valve node is a top-level node, physically located at the upstream end of the target building's pipe network, then the number *a* of its neighbor nodes is typically 1, and the unique neighbor node is the downstream neighbor node. The current pressure drop can be obtained by subtracting the second real-time pressure of this downstream neighbor node from the first real-time pressure; no specific limitation is made here.

[0057] Next, the first intelligent water valve node estimates the current local hydraulic impedance based on the current pressure drop and the first instantaneous flow rate, using a preset pipeline hydraulic state equation. The preset pipeline hydraulic state equation can be defined as: ΔP i =R i ×Q i ². Wherein, ΔP i The current pressure drop; i represents the first smart water valve node; Q i R is the first instantaneous flow rate; iThe current local hydraulic impedance is defined as follows. When the first instantaneous flow rate approaches zero, to avoid numerical instability caused by division operations, a lower flow rate threshold can be set. When the first instantaneous flow rate is lower than this threshold, the local hydraulic impedance estimated in the previous control cycle remains unchanged. Then, the first intelligent water valve node acquires its own first desired pressure and the historical instantaneous flow rate from the previous control cycle. The first desired pressure represents the target downstream pressure value that the first intelligent water valve node expects to maintain in collaborative control. This pressure can be uniformly issued by the cloud management platform according to the global optimization objective, or it can be pre-stored in local memory. The historical instantaneous flow rate represents the first instantaneous flow rate collected and recorded in the previous control cycle, used to construct the flow smoothing term in the local cost function to suppress drastic fluctuations in flow commands between adjacent control cycles.

[0058] Then, the current local hydraulic impedance, first real-time pressure, first instantaneous flow rate, first expected pressure, historical instantaneous flow rate, *a* second real-time pressures, and *a* neighbor predicted pressure sequences are summarized to obtain the first parameter set. Based on the local cost function and constraints, the predicted state information and target hydraulic impedance sequence are determined according to the first parameter set.

[0059] It is evident that by acquiring the local real-time status and the current and predicted information of neighbors, and combining the target topology map to determine the upstream and downstream relationships, the current pressure drop and local hydraulic impedance can be accurately calculated. Furthermore, the expected pressure and historical flow can be integrated to construct a complete set of first parameters, laying a precise data foundation for the rolling optimization solution of distributed model predictive control. This enables each node to make collaborative decisions while fully considering the future behavior of its neighbors.

[0060] For easier understanding, please refer to Figure 6 , Figure 6 This is a flowchart illustrating a distributed model predictive control solution method provided in an embodiment of this application. The specific steps of determining the predicted state information and the target hydraulic impedance sequence based on the local cost function and the constraints, according to the first parameter set, include: S41. Using the first real-time pressure and the first instantaneous flow rate in the first parameter set as the initial state, and the current local hydraulic impedance as the model parameter, establish a valve hydraulic state prediction model in the prediction time domain. S42. Based on the constraints and the current local hydraulic impedance, generate multiple candidate hydraulic impedance sequences; S43. Using the valve hydraulic state prediction model, based on the a second real-time pressures and the multiple candidate hydraulic impedance sequences in the first parameter set, determine multiple first predicted pressure sequences and multiple first predicted flow sequences. S44. Based on the local cost function and the constraint conditions, the target hydraulic impedance sequence is obtained by minimizing the first parameter set, the plurality of first predicted pressure sequences and the plurality of first predicted flow sequences. S45. Determine the first predicted pressure sequence corresponding to the target hydraulic impedance sequence among the plurality of first predicted pressure sequences as the predicted state information.

[0061] In a specific embodiment, firstly, the first intelligent water valve node uses the first real-time pressure and the first instantaneous flow rate from the first parameter set as its initial state, and uses the current local hydraulic impedance as the model parameter to establish a valve hydraulic state prediction model (i.e., a distributed model) in the prediction time domain. The valve hydraulic state prediction model includes the pipeline hydraulic state equation and the pressure drop equation. The pipeline hydraulic state equation is: ΔP i (k)=R i (k)×Q i (k)², this pipeline hydraulic state equation is used to describe the pressure drop ΔP flowing through the valve in the k-th control cycle within the prediction time domain. i (k) and the flow rate Q through the valve i (k) and the hydraulic resistance R applied during this period i The quantitative relationship between (k); Pressure drop equation: ΔP i (k)=P up (k)-P i (k), where P up (k) represents the pressure upstream of the first intelligent water valve node in the kth control cycle, P i (k) represents the predicted pressure after the valve of the first smart water valve node in this cycle.

[0062] Then, the first intelligent water valve node generates multiple candidate hydraulic impedance sequences based on the constraints and *a* second real-time pressures. The constraints include pressure constraints, flow constraints, and valve mechanical limitation constraints, which are not specifically defined here. The pressure constraint is: P... i,min ≤P i ≤P i,max P i P represents the predicted downstream pressure of the first intelligent water valve node in each control cycle within the prediction time domain. i,min P is the preset lower pressure limit. i,max This pressure constraint, set as a preset upper limit, is used to ensure the water supply pressure at the most unfavorable point in the target building's pipe network. The flow constraint is: Q. i ≥0, Q i To predict the flow rate through the valve in each control cycle within the time domain, this flow constraint ensures the physical rationality of the flow rate, meaning the water flow direction is always from upstream to downstream, with no reverse flow. The valve mechanical constraint is: Ri,min ≤R i ≤R i,max R i To predict the hydraulic impedance value of the valve in each control cycle within the time domain, R i,min R is the minimum hydraulic resistance when the valve is fully open. i,max The maximum hydraulic resistance of the valve when it is nearly fully closed is represented by the valve's mechanical constraint, which directly reflects the physical stroke limitation of the valve actuator. i,min and R i,max The specific values ​​are determined by the valve's mechanical structure and flow characteristic curve, obtained through calibration tests before the valve leaves the factory, and written into the local controller of each intelligent water valve node during installation. Among these, the impedance range [R] is [not specified]. i,min R i,max Within a given range, using the current local hydraulic impedance as a reference, multiple hydraulic impedance value sequences of length c are generated according to a preset step size or sampling strategy. For example, the current local hydraulic impedance can be used as the center, and several discrete values ​​can be taken within a certain range above and below it (such as ±20%) with equal step sizes. These discrete values ​​can then be arranged and combined into multiple candidate hydraulic impedance sequences.

[0063] Next, for the first control cycle in the prediction time domain, the valve hydraulic state prediction model starts with the first real-time pressure and the first instantaneous flow rate, uses the first hydraulic impedance value in the candidate hydraulic impedance sequence, and takes the pressure of the neighboring node as a second real-time pressure (i.e., the measured pressure of the neighboring node at the current moment), substitutes it into the equation of the valve hydraulic state prediction model, and calculates the predicted pressure and predicted flow rate of the first smart water valve node in the first control cycle. For subsequent control cycles in the prediction time domain, the valve hydraulic state prediction model starts with the predicted state of the previous cycle, uses the corresponding hydraulic impedance value in the candidate hydraulic impedance sequence, and switches the pressure of the neighboring node to the predicted pressure value at the corresponding moment in the a neighboring predicted pressure sequence, and continues iterative calculation until the derivation of the entire prediction time domain is completed, resulting in multiple first predicted pressure sequences and multiple first predicted flow rate sequences. Each candidate hydraulic impedance sequence generates a corresponding first predicted pressure sequence and a first predicted flow rate sequence.

[0064] Then, based on the local cost function and constraints, the target hydraulic impedance sequence is obtained by minimizing the first parameter set, the multiple first predicted pressure sequences, and the multiple first predicted flow sequences. Finally, the first predicted pressure sequence corresponding to the target hydraulic impedance sequence among the multiple first predicted pressure sequences is used as the prediction state information. This prediction state information contains the predicted downstream pressure values ​​of the first smart valve node in each control cycle within the prediction time domain, and will be broadcast to a second smart valve nodes via a wireless communication module at the end of the current control cycle. This allows neighboring nodes to use it as input parameters when performing their respective optimization solutions in the next control cycle, thereby realizing information closure and collaborative iteration among the nodes.

[0065] It is evident that by establishing a valve hydraulic state prediction model to infer candidate impedance sequences and combining it with the local cost function for minimization, each smart valve node can autonomously decide on the optimal adjustment scheme based on considering the future behavior of its neighbors, taking into account multiple control objectives such as pressure tracking, neighbor collaboration, and flow smoothing. At the same time, it broadcasts the generated predicted pressure sequence to neighbor nodes, forming an information closed loop and realizing decentralized collaborative rolling optimization of the entire pipeline network.

[0066] The specific steps for obtaining the target hydraulic impedance sequence by minimizing the target hydraulic impedance sequence based on the local cost function and the constraints, according to the first parameter set, multiple first predicted pressure sequences, and multiple first predicted flow sequences, include: S51. Based on the local cost function, according to the first expected pressure, the historical instantaneous flow rate, and the a neighbor predicted pressure sequences in the first parameter set, as well as the plurality of first predicted pressure sequences and the plurality of first predicted flow rate sequences, calculate the cost function values ​​corresponding to the plurality of candidate hydraulic impedance sequences to obtain a plurality of cost function values; the local cost function includes at least a pressure tracking deviation term, a flow fluctuation suppression term, and a neighbor pressure consistency term; S52. The cost function value that satisfies the constraint and is the smallest among the plurality of cost function values ​​is taken as the target cost function value; S53. Determine the candidate hydraulic impedance sequence corresponding to the target cost function value among the plurality of candidate hydraulic impedance sequences as the target hydraulic impedance sequence.

[0067] In a specific embodiment, the local cost function is as follows: J i =α×(P i (k)-P i,desired )²+β×Σ j∈N(i) (P i (k)-P j (k))²+γ×(Q i (k)-(Qi (k-1))².

[0068] Among them, J i Let P be the local cost function value of the first intelligent water valve node i. i (k) represents the predicted pressure of the first intelligent water valve node in the kth control cycle; P i,desired The first desired pressure for the first intelligent water valve node; P j (k) represents the pressure value of the j-th second intelligent water valve node in the k-th control cycle. In the first step of the prediction time domain (at time k=0), P j (0) takes the value of a second real-time pressure (i.e., the measured pressure of the neighbor at the current moment) in the first parameter set; in subsequent steps in the prediction time domain (k≥1), P j (k) takes the predicted pressure value at the corresponding time from the predicted pressure sequences of a neighbors; Q i (k) represents the predicted flow rate of the first intelligent water valve node in the kth control cycle; Q i (k-1) represents the flow rate value of the previous control cycle. When k=0, Q i (k-1) represents the historical instantaneous flow rate in the first parameter set; N(i) represents the set of neighboring nodes of the first intelligent water valve node, i.e., a second intelligent water valve nodes; α is the pressure tracking weight coefficient, used to adjust the importance of tracking the desired pressure; β is the neighbor pressure consistency weight coefficient, used to adjust the importance of aligning with the pressure of neighboring nodes, and is the core parameter for achieving global pressure coordination and balance; γ is the flow smoothing weight coefficient, used to suppress drastic changes in flow commands between adjacent control cycles, protect the pipeline, and extend the life of the valve actuator.

[0069] The first intelligent water valve node calculates the cost function value corresponding to each candidate hydraulic impedance sequence based on this local cost function, thus obtaining multiple cost function values ​​corresponding to multiple candidate hydraulic impedance sequences. It should be noted that the pressure tracking deviation term is α×(P) i (k)-P i,desired )², the flow fluctuation suppression term is β×Σ j∈N(i) (P i (k)-P j (k))², the neighbor pressure consistency term is γ×(Q) i (k)-(Q i (k-1))².

[0070] Then, for each candidate hydraulic impedance sequence and its corresponding first predicted pressure sequence and first predicted flow sequence, the state variables and control variables for each control cycle in the prediction time domain are verified one by one to ensure that they all meet the constraints. For candidate hydraulic impedance sequences that do not meet the constraints, their corresponding cost function values ​​are directly excluded and not included in subsequent comparisons. For candidate hydraulic impedance sequences that meet the constraints, their cost function values ​​are compared, and the smallest cost function value is selected as the target cost function value. Finally, from multiple candidate hydraulic impedance sequences, the candidate hydraulic impedance sequence corresponding to the target cost function value is obtained and determined as the target hydraulic impedance sequence for the current control cycle.

[0071] It is evident that by constructing a multi-objective cost function that integrates pressure tracking, neighbor collaboration, and flow smoothing, the candidate hydraulic impedance sequences are quantitatively evaluated. Under the premise of satisfying constraints, the sequence with the minimum cost is selected as the optimal control scheme. This ensures that the valve regulation decision in each control cycle can guarantee the safety of the pipeline pressure and the physical limits of the equipment, while also taking into account multiple control qualities such as water supply accuracy, system stability, and pipeline protection under dynamic operating conditions.

[0072] Step S505: Determine the valve opening command based on the target hydraulic impedance sequence, and drive the valve mechanical components according to the valve opening command in the next control cycle.

[0073] For easier understanding, please refer to Figure 7 , Figure 7 This is a flowchart illustrating a method for determining a valve opening command according to an embodiment of this application. The steps include determining the valve opening command based on the target hydraulic impedance sequence, and driving the valve mechanical components according to the valve opening command in the next control cycle. S61. Extract the first target hydraulic impedance from the target hydraulic impedance sequence to obtain the execution impedance of the next control cycle; S62. Based on the preset mapping relationship between hydraulic impedance and valve opening, the execution impedance is converted into the corresponding valve opening value to obtain the valve opening command; S63. Send the valve opening command to the valve mechanical component to drive the valve mechanical component to adjust to the opening position corresponding to the valve opening value.

[0074] In a specific embodiment, firstly, the first intelligent water valve node extracts the first target hydraulic impedance value from the target hydraulic impedance sequence as the execution impedance for the next control cycle. This effectively addresses model mismatch and external disturbances in actual operating conditions, ensuring real-time robustness of the control. Then, based on a preset mapping relationship between hydraulic impedance and valve opening, the execution impedance is converted into a corresponding valve opening value, forming a valve opening command. Specifically, before the valve leaves the factory or during installation and commissioning, the hydraulic impedance values ​​of the valve at different openings can be experimentally calibrated to establish a mapping relationship between hydraulic impedance and valve opening, which is then stored in the local controller of the first intelligent water valve node. Next, the first intelligent water valve node sends the valve opening command to the drive unit of the valve's mechanical components (such as a stepper motor driver or servo motor controller), driving the valve's mechanical components to adjust to the target opening position. Based on the received opening command, the valve's mechanical components move the valve core by rotating the motor, changing the valve's flow cross-sectional area, thereby adjusting the hydraulic impedance.

[0075] It is evident that the rolling optimization strategy only executes the first value of the target hydraulic impedance sequence and converts it into a physical command that can directly drive the valve through the impedance-opening mapping relationship. This achieves precise connection between algorithm decision-making and physical execution while taking into account the ability to respond quickly to changes in real-time operating conditions and the smooth adjustment of the valve actuator.

[0076] Step S506: The predicted state information is broadcast to the a second smart water valve nodes through the wireless communication module to coordinate the pressure distribution of the target building pipe network.

[0077] Specifically, after completing the distributed model predictive control solution for the current control cycle and obtaining the predicted state information, the first intelligent water valve node encapsulates this predicted state information into a data packet and transmits it via wireless communication module to a determined second intelligent water valve nodes in the target topology map through broadcast or directional transmission. The predicted state information includes the predicted pressure sequence after the valve for each control cycle in the future prediction time domain for the first intelligent water valve node. Its data format is consistent with the predicted pressure sequences of its neighbors, facilitating direct parsing and use by the receiving nodes.

[0078] As can be seen, by continuously exchanging predicted state information within each control cycle, all smart water valve nodes can promptly obtain the future pressure change trends of their neighbors and consider them in the neighbor pressure consistency term of their respective local cost functions. Through information exchange and collaborative iteration, the pressure distribution of the entire target building's pipe network gradually converges to an equilibrium state, meaning that the pressure of each floor, while meeting its own desired pressure, tends to be consistent with the pressure of its neighboring floors. This achieves decentralized collaborative regulation and improves the intelligence level and adaptive capability of the building's pipe network's hydraulic balance control.

[0079] The above primarily describes the solutions of the embodiments of this application from the perspective of the method execution process. It is understood that, in order to achieve the above functions, the electronic device includes corresponding hardware structures and / or software modules for executing each function. Those skilled in the art should readily recognize that, in conjunction with the units and algorithm steps of the various examples described in the embodiments provided herein, this application can be implemented in hardware or a combination of hardware and computer software. Whether a function is executed by hardware or by computer software driving hardware depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0080] This application embodiment can divide the electronic device into functional units according to the above method example. For example, each function can be divided into a separate functional unit, or two or more functions can be integrated into one processing unit. The integrated unit can be implemented in hardware or as a software functional unit. It should be noted that the unit division in this application embodiment is illustrative and only represents one logical functional division. In actual implementation, there may be other division methods.

[0081] When dividing each function into modules according to its corresponding function. Figure 8 This is a functional module block diagram of a smart water valve collaborative optimization device for building scenarios provided in this application embodiment. The smart water valve collaborative optimization device 800 for building scenarios is applied to a first smart water valve node in a smart water valve collaborative control system. The smart water valve collaborative control system includes N smart water valve nodes, which are distributed and installed in the target building's pipe network, where N is an integer greater than 1. The first smart water valve node is any one of the N smart water valve nodes. The first smart water valve node is equipped with valve mechanical components and a wireless communication module. The smart water valve collaborative optimization device 800 for building scenarios includes a first acquisition module 810, a first determination module 820, a second acquisition module 830, a processing module 840, a second determination module 850, and a broadcast module 860, wherein: The first acquisition module 810 is used to acquire a target topology map of the target building's pipe network; the target topology map is used to characterize the physical pipe connection relationship between each smart water valve node in the target building's pipe network; The first determining module 820 is used to determine the neighboring nodes of the first smart water valve node according to the target topology map, and obtain a second smart water valve nodes; a is a positive integer less than or equal to 2; The second acquisition module 830 is used to acquire the local status information of the first smart water valve node based on a preset control cycle, and to acquire the status information of a neighbors corresponding to the a second smart water valve nodes through the wireless communication module. The processing module 840 is used to solve the local state information and the state information of the a neighboring states based on a preset local cost function and constraints to obtain the predicted state information and the target hydraulic impedance sequence. The second determining module 850 is used to determine the valve opening command according to the target hydraulic impedance sequence, and drive the valve mechanical components according to the valve opening command in the next control cycle; The broadcast module 860 is used to broadcast the predicted state information to the a second smart water valve nodes through the wireless communication module in order to coordinate the pressure distribution of the target building pipe network.

[0082] Optionally, the first intelligent water valve node is also equipped with a pressure sensor. Before acquiring the target topology map of the target building's pipe network, the processing module 840 is specifically used for: The wireless communication module receives neighbor discovery requests broadcast from b second smart water valve nodes, thus obtaining b neighbor discovery requests; the b second smart water valve nodes are all neighboring nodes of the first smart water valve node among N-1 smart water valve nodes; b is an integer greater than or equal to a and less than N-1; Obtain the b node identifiers and b pulse codes carried in the b neighbor discovery requests; Determine the b reception times and b wireless signal strengths corresponding to the b neighbor discovery requests; Based on the b pulse codes, the pressure fluctuations within the pipes of the target building's pipe network are matched and detected by the pressure sensor to obtain b pressure pulses; the b pressure pulses correspond one-to-one with the b pulse codes; Determine the b arrival times corresponding to the b pressure pulses; The propagation time is determined based on the b reception times and the b arrival times; The b hydraulic distances in the pipeline are determined based on the preset pulse propagation speed and the b propagation times; the hydraulic distance in the pipeline represents the actual physical path length of the pressure pulse propagating inside a water-filled pipeline. Based on the strength of the b wireless signals and the hydraulic distance of the b pipelines, the b second smart water valve nodes are filtered to obtain the a second smart water valve nodes; the a second smart water valve nodes are used to construct the target topology map.

[0083] Optionally, in the step of filtering the b second smart water valve nodes based on the b wireless signal strengths and the b hydraulic distances in the pipeline to obtain the a second smart water valve nodes, the processing module 840 is specifically used for: Obtain the length of the vertical main pipe and the length of the horizontal branch pipe corresponding to the target building's pipe network; the length of the vertical main pipe is the length of the vertical pipe segment connecting two adjacent smart water valve nodes; the length of the horizontal branch pipe is the length of the horizontal pipe segment from the main pipe branch interface to the smart water valve node on each floor. The reference hydraulic distance is determined based on the length of the vertical main pipe and the length of the horizontal branch pipe. The hydraulic distance range of the pipeline is determined based on the preset reference ratio and the reference pipeline hydraulic distance; The b second intelligent water valve nodes are filtered according to reference screening conditions to obtain a second intelligent water valve nodes; the reference screening conditions are that the hydraulic distance of the pipeline is within the hydraulic distance range of the pipeline and the wireless signal strength is greater than the preset signal strength threshold.

[0084] Optionally, in the process of solving the local state information and the state information of the a neighboring states based on a preset local cost function and constraints to obtain the predicted state information and the target hydraulic impedance sequence, the processing module 840 is specifically used for: Obtain the first real-time pressure and the first instantaneous flow rate from the local status information; Obtain a second real-time pressure, a second instantaneous flow rate, and a neighbor predicted pressure sequence from the a neighbor status information; the a neighbor predicted pressure sequence is the predicted pressure data in the prediction time domain generated and broadcast by the a second smart water valve nodes in the previous control cycle; the prediction time domain includes c control cycles; c is a positive integer less than or equal to 3; Based on the target topology, determine the upstream neighbor node of the first smart water valve node from the a second smart water valve nodes; The current pressure drop is determined based on the second real-time pressure corresponding to the upstream neighbor node in the a second real-time pressure and the first real-time pressure; Based on the current pressure drop and the first instantaneous flow rate, the current local hydraulic impedance is estimated according to the preset pipeline hydraulic state equation. Obtain the first desired pressure and the historical instantaneous flow rate of the first intelligent water valve node in the previous control cycle; A first parameter set is determined based on the current local hydraulic impedance, the first real-time pressure, the first instantaneous flow rate, the first expected pressure, the historical instantaneous flow rate, the a second real-time pressures, and the a neighbor predicted pressure sequences; Based on the local cost function and the constraints, the predicted state information and the target hydraulic impedance sequence are determined according to the first parameter set.

[0085] Optionally, in determining the predicted state information and the target hydraulic impedance sequence based on the first parameter set according to the local cost function and the constraints, the processing module 840 is specifically used for: Using the first real-time pressure and the first instantaneous flow rate in the first parameter set as the initial state, and the current local hydraulic impedance as the model parameter, a valve hydraulic state prediction model in the prediction time domain is established. Based on the constraints and the current local hydraulic impedance, multiple candidate hydraulic impedance sequences are generated. Based on the valve hydraulic state prediction model, a plurality of first predicted pressure sequences and a plurality of first predicted flow sequences are determined according to the a second real-time pressures and the plurality of candidate hydraulic impedance sequences in the first parameter set. Based on the local cost function and the constraints, the target hydraulic impedance sequence is obtained by minimizing the first parameter set, the plurality of first predicted pressure sequences and the plurality of first predicted flow sequences. The first predicted pressure sequence corresponding to the target hydraulic impedance sequence among the plurality of first predicted pressure sequences is determined as the predicted state information.

[0086] Optionally, in the process of minimizing the target hydraulic impedance sequence based on the local cost function and the constraints, according to the first parameter set, multiple first predicted pressure sequences, and multiple first predicted flow sequences, the processing module 840 is specifically used for: Based on the local cost function, according to the first expected pressure, the historical instantaneous flow rate, and the a neighbor predicted pressure sequences in the first parameter set, as well as the plurality of first predicted pressure sequences and the plurality of first predicted flow rate sequences, the cost function values ​​corresponding to the plurality of candidate hydraulic impedance sequences are calculated to obtain a plurality of cost function values; the local cost function includes at least a pressure tracking deviation term, a flow fluctuation suppression term, and a neighbor pressure consistency term; The cost function value that satisfies the constraints and is the smallest among the plurality of cost function values ​​is taken as the target cost function value; The candidate hydraulic impedance sequence corresponding to the target cost function value among the plurality of candidate hydraulic impedance sequences is determined as the target hydraulic impedance sequence.

[0087] Optionally, in determining the valve opening command based on the target hydraulic impedance sequence and driving the valve mechanical components according to the valve opening command in the next control cycle, the second determining module 850 is specifically used for: Extract the first target hydraulic impedance from the target hydraulic impedance sequence to obtain the execution impedance of the next control cycle; Based on the preset mapping relationship between hydraulic impedance and valve opening, the execution impedance is converted into the corresponding valve opening value to obtain the valve opening command; The valve opening command is sent to the valve mechanical component to drive the valve mechanical component to adjust to the opening position corresponding to the valve opening value.

[0088] It should be noted that the specific implementation of each operation can be described in the corresponding description of the method embodiments shown above. The intelligent water valve collaborative optimization device 800 for building scenarios can be used to execute the above method embodiments of this application, and will not be described again here.

[0089] This application also provides a computer-readable storage medium storing a computer program for electronic data interchange, which causes a computer to perform some or all of the steps of any of the methods described in the above method embodiments, wherein the computer includes an electronic device.

[0090] This application also provides a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program operable to cause a computer to perform some or all of the steps of any of the methods described in the above method embodiments. The computer program product may be a software installation package, and the computer may include an electronic device.

[0091] It should be noted that, for the sake of simplicity, the above embodiments are all described as a series of actions. Those skilled in the art should understand that this application is not limited to the described order of actions, as some steps in the embodiments of this application can be performed in other orders or simultaneously. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are preferred embodiments, and the actions, steps, modules, or units involved are not necessarily essential to the embodiments of this application.

[0092] In the above embodiments, the descriptions of each embodiment in this application have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.

[0093] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. This program can be stored in a computer-readable storage medium, and when executed, it can include the processes described in the above method embodiments. The aforementioned storage medium includes various media capable of storing program code, such as ROM or random access memory (RAM), magnetic disks, or optical disks.

[0094] The steps of the methods or algorithms described in the embodiments of this application can be implemented in hardware or by a processor executing software instructions. The software instructions can consist of corresponding software modules, which can be stored in RAM, flash memory, ROM, EPROM, electrically erasable programmable read-only memory (EEPROM), registers, hard disk, portable hard disk, read-only optical disk (CD-ROM), or any other form of storage medium well known in the art. An exemplary storage medium is coupled to a processor, enabling the processor to read information from and write information to the storage medium. Of course, the storage medium can also be a component of the processor. The processor and storage medium can reside in an ASIC. Furthermore, the ASIC can reside in a terminal device or management device. Alternatively, the processor and storage medium can exist as discrete components in the terminal device or management device.

[0095] Those skilled in the art will recognize that, in one or more of the examples above, the functions described in the embodiments of this application can be implemented, in whole or in part, by software, hardware, firmware, or any combination thereof. When implemented in software, it can be implemented, in whole or in part, as a computer program product. This computer program product includes one or more computer instructions. When these computer program instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of this application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium accessible to a computer or a data storage device such as a server or data center that integrates one or more available media. The available media can be magnetic media (e.g., floppy disks, hard disks, magnetic tapes), optical media (e.g., digital video discs (DVDs)), or semiconductor media (e.g., solid-state disks (SSDs)).

[0096] The modules / units included in the various devices and products described in the above embodiments can be software modules / units, hardware modules / units, or a combination of both. For example, for devices and products applied to or integrated into a chip, all modules / units can be implemented using hardware methods such as circuits, or at least some modules / units can be implemented using software programs that run on a processor integrated within the chip, while the remaining (if any) modules / units can be implemented using hardware methods such as circuits. For devices and products applied to or integrated into a chip module, all modules / units can be implemented using hardware methods such as circuits. Different modules / units can be located in the same component (e.g., chip, circuit module, etc.) or different components of the chip module, or at least some modules / units can be implemented using hardware methods such as circuits. The implementation is achieved through a software program that runs on the processor integrated within the chip module. The remaining modules / units (if any) can be implemented using hardware methods such as circuits. For various devices and products applied to or integrated into terminal equipment, each of their modules / units can be implemented using hardware methods such as circuits. Different modules / units can be located in the same component (e.g., chip, circuit module, etc.) or different components within the terminal equipment. Alternatively, at least some modules / units can be implemented through a software program that runs on the processor integrated within the terminal equipment, while the remaining modules / units (if any) can be implemented using hardware methods such as circuits.

[0097] The specific embodiments described above further illustrate the purpose, technical solution, and beneficial effects of the embodiments of this application. It should be understood that the above descriptions are merely specific embodiments of the embodiments of this application and are not intended to limit the protection scope of the embodiments of this application. Any modifications, equivalent substitutions, improvements, etc., made on the basis of the technical solutions of the embodiments of this application should be included within the protection scope of the embodiments of this application.

Claims

1. A method for intelligent water valve collaborative optimization in building scenarios, characterized in that, The first intelligent water valve node is applied in the intelligent water valve collaborative control system, which includes N intelligent water valve nodes. The N intelligent water valve nodes are distributed and installed in the target building pipe network, where N is an integer greater than 1; the first intelligent water valve node is any one of the N intelligent water valve nodes. The first intelligent water valve node is equipped with valve mechanical components and a wireless communication module, and the method includes: Obtain the target topology map of the target building's pipe network; the target topology map is used to characterize the physical pipe connection relationships between each smart water valve node in the target building's pipe network; Based on the target topology graph, determine the neighboring nodes of the first smart water valve node to obtain a second smart water valve nodes; a is a positive integer less than or equal to 2. Based on a preset control cycle, the local status information of the first smart water valve node is obtained, and the status information of the a neighbors corresponding to the a second smart water valve nodes is obtained through the wireless communication module. Based on the preset local cost function and constraints, the predicted state information and the target hydraulic impedance sequence are obtained by solving the problem according to the local state information and the state information of the a neighbors. The valve opening command is determined based on the target hydraulic impedance sequence, and the valve mechanical components are driven according to the valve opening command in the next control cycle. The predicted state information is broadcast to the a second intelligent water valve nodes via the wireless communication module to coordinate the pressure distribution of the target building's pipe network.

2. The method as described in claim 1, characterized in that, The first intelligent water valve node is also equipped with a pressure sensor. Before acquiring the target topology map of the target building's pipe network, the method further includes: The wireless communication module receives neighbor discovery requests broadcast from b second smart water valve nodes, thus obtaining b neighbor discovery requests; the b second smart water valve nodes are all neighboring nodes of the first smart water valve node among N-1 smart water valve nodes; b is an integer greater than or equal to a and less than N-1; Obtain the b node identifiers and b pulse codes carried in the b neighbor discovery requests; Determine the b reception times and b wireless signal strengths corresponding to the b neighbor discovery requests; Based on the b pulse codes, the pressure fluctuations within the pipes of the target building's pipe network are matched and detected by the pressure sensor to obtain b pressure pulses; the b pressure pulses correspond one-to-one with the b pulse codes; Determine the b arrival times corresponding to the b pressure pulses; The propagation time is determined based on the b reception times and the b arrival times; The b hydraulic distances in the pipeline are determined based on the preset pulse propagation speed and the b propagation times; the hydraulic distance in the pipeline represents the actual physical path length of the pressure pulse propagating inside a water-filled pipeline. Based on the strength of the b wireless signals and the hydraulic distance of the b pipelines, the b second smart water valve nodes are filtered to obtain the a second smart water valve nodes; the a second smart water valve nodes are used to construct the target topology map.

3. The method as described in claim 2, characterized in that, The step of filtering the b second smart water valve nodes based on the b wireless signal strengths and the b hydraulic distances in the pipeline to obtain the a second smart water valve nodes includes: Obtain the length of the vertical main pipe and the length of the horizontal branch pipe corresponding to the target building's pipe network; the length of the vertical main pipe is the length of the vertical pipe segment connecting two adjacent smart water valve nodes; the length of the horizontal branch pipe is the length of the horizontal pipe segment from the main pipe branch interface to the smart water valve node on each floor. The reference hydraulic distance is determined based on the length of the vertical main pipe and the length of the horizontal branch pipe. The hydraulic distance range of the pipeline is determined based on the preset reference ratio and the reference pipeline hydraulic distance; The b second intelligent water valve nodes are filtered according to reference screening conditions to obtain a second intelligent water valve nodes; the reference screening conditions are that the hydraulic distance of the pipeline is within the hydraulic distance range of the pipeline and the wireless signal strength is greater than the preset signal strength threshold.

4. The method as described in claim 1, characterized in that, The method, based on a preset local cost function and constraints, solves the problem according to the local state information and the state information of a neighboring states to obtain the predicted state information and the target hydraulic impedance sequence, including: Obtain the first real-time pressure and the first instantaneous flow rate from the local status information; Obtain a second real-time pressure, a second instantaneous flow rate, and a neighbor predicted pressure sequence from the a neighbor status information; the a neighbor predicted pressure sequence is the predicted pressure data in the prediction time domain generated and broadcast by the a second smart water valve nodes in the previous control cycle; the prediction time domain includes c control cycles; c is a positive integer less than or equal to 3; Based on the target topology, determine the upstream neighbor node of the first smart water valve node from the a second smart water valve nodes; The current pressure drop is determined based on the second real-time pressure corresponding to the upstream neighbor node in the a second real-time pressure and the first real-time pressure; Based on the current pressure drop and the first instantaneous flow rate, the current local hydraulic impedance is estimated according to the preset pipeline hydraulic state equation. Obtain the first desired pressure and the historical instantaneous flow rate of the first intelligent water valve node in the previous control cycle; A first parameter set is determined based on the current local hydraulic impedance, the first real-time pressure, the first instantaneous flow rate, the first expected pressure, the historical instantaneous flow rate, the a second real-time pressures, and the a neighbor predicted pressure sequences; Based on the local cost function and the constraints, the predicted state information and the target hydraulic impedance sequence are determined according to the first parameter set.

5. The method as described in claim 4, characterized in that, The step of determining the predicted state information and the target hydraulic impedance sequence based on the local cost function and the constraints, according to the first parameter set, includes: Using the first real-time pressure and the first instantaneous flow rate in the first parameter set as the initial state, and the current local hydraulic impedance as the model parameter, a valve hydraulic state prediction model in the prediction time domain is established. Based on the constraints and the current local hydraulic impedance, multiple candidate hydraulic impedance sequences are generated. Based on the valve hydraulic state prediction model, a plurality of first predicted pressure sequences and a plurality of first predicted flow sequences are determined according to the a second real-time pressures and the plurality of candidate hydraulic impedance sequences in the first parameter set. Based on the local cost function and the constraints, the target hydraulic impedance sequence is obtained by minimizing the first parameter set, the plurality of first predicted pressure sequences and the plurality of first predicted flow sequences. The first predicted pressure sequence corresponding to the target hydraulic impedance sequence among the plurality of first predicted pressure sequences is determined as the predicted state information.

6. The method as described in claim 5, characterized in that, The process of minimizing the target hydraulic impedance sequence based on the local cost function and the constraints, according to the first parameter set, multiple first predicted pressure sequences, and multiple first predicted flow sequences, includes: Based on the local cost function, according to the first expected pressure, the historical instantaneous flow rate, and the a neighbor predicted pressure sequences in the first parameter set, as well as the plurality of first predicted pressure sequences and the plurality of first predicted flow rate sequences, the cost function values ​​corresponding to the plurality of candidate hydraulic impedance sequences are calculated to obtain a plurality of cost function values; the local cost function includes at least a pressure tracking deviation term, a flow fluctuation suppression term, and a neighbor pressure consistency term; The cost function value that satisfies the constraints and is the smallest among the plurality of cost function values ​​is taken as the target cost function value; The candidate hydraulic impedance sequence corresponding to the target cost function value among the plurality of candidate hydraulic impedance sequences is determined as the target hydraulic impedance sequence.

7. The method according to any one of claims 1-6, characterized in that, The step of determining the valve opening command based on the target hydraulic impedance sequence and driving the valve mechanical components according to the valve opening command in the next control cycle includes: Extract the first target hydraulic impedance from the target hydraulic impedance sequence to obtain the execution impedance of the next control cycle; Based on the preset mapping relationship between hydraulic impedance and valve opening, the execution impedance is converted into the corresponding valve opening value to obtain the valve opening command; The valve opening command is sent to the valve mechanical component to drive the valve mechanical component to adjust to the opening position corresponding to the valve opening value.

8. A smart water valve collaborative optimization device for building scenarios, characterized in that, A first intelligent water valve node is applied in an intelligent water valve collaborative control system. The intelligent water valve collaborative control system includes N intelligent water valve nodes, which are distributed and installed in the target building's pipe network, where N is an integer greater than 1. The first intelligent water valve node is any one of the N intelligent water valve nodes. The first intelligent water valve node is equipped with valve mechanical components and a wireless communication module. The device includes a first acquisition module, a first determination module, a second acquisition module, a processing module, a second determination module, and a broadcast module, wherein: The first acquisition module is used to acquire a target topology map of the target building's pipe network; the target topology map is used to characterize the physical pipe connection relationship between each smart water valve node in the target building's pipe network; The first determining module is used to determine the neighboring nodes of the first smart water valve node according to the target topology map, and obtain a second smart water valve nodes; a is a positive integer less than or equal to 2; The second acquisition module is used to acquire the local status information of the first smart water valve node based on a preset control cycle, and to acquire the status information of a neighbors corresponding to the a second smart water valve nodes through the wireless communication module. The processing module is used to solve the local state information and the state information of the a neighboring states based on a preset local cost function and constraints to obtain the predicted state information and the target hydraulic impedance sequence. The second determining module is used to determine the valve opening command based on the target hydraulic impedance sequence, and drive the valve mechanical components according to the valve opening command in the next control cycle; The broadcast module is used to broadcast the predicted state information to the a second smart water valve nodes through the wireless communication module in order to coordinate the pressure distribution of the target building pipe network.

9. An electronic device, characterized in that, include: Processor, memory, communication interface, and one or more programs; The one or more programs are stored in the memory and configured to be executed by the processor, the programs including instructions for performing the steps of the method as described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, the computer program including program instructions that, when executed by a processor, cause the processor to perform the method as described in any one of claims 1-7.

Images