Intelligent regulation and control method and system for secondary water supply

Abstract

The invention provides a secondary water supply intelligent regulation and control method and system, and the method comprises the steps: building a corresponding twin model based on the connection relation of all equipment in a secondary water supply system, and enabling the twin model to at least comprise a water tank twin module, a pipeline twin module and an auxiliary equipment twin module; segmenting the twinborn model based on a water tank twinborn module to obtain a plurality of water supply twinborn paths; the working state of each twin module in the twin model is obtained to obtain first state information, and the water quality information and the water flow information are detected and processed based on corresponding multi-modal Internet of Things acquisition equipment in each water tank twin module to obtain multi-modal detection information; inputting the multi-modal detection information into a pre-configured regulation and control neural network, and sequentially calculating, analyzing and processing based on neurons in the regulation and control neural network to obtain an intelligent regulation and control strategy of the secondary water supply system; and the regulation and control information of each module in the twin model is generated based on the intelligent regulation and control strategy, and the corresponding entity equipment is regulated and controlled, so that the water supply efficiency of the user is improved.

Description

Technical Field

[0001] The present invention relates to data processing technology, and in particular to a secondary water supply intelligent control method and system. Background Art

[0002] With the acceleration of urbanization, secondary water supply systems play an increasingly important role in urban water resource management. Secondary water supply systems deliver municipal tap water to high-rise buildings and residential areas to ensure that users can get a stable water supply even during peak hours. However, traditional secondary water supply management methods mostly rely on manual monitoring, resulting in problems such as low water supply efficiency, increased energy consumption and waste of water resources.

[0003] At present, the regulation technology of secondary water supply systems mainly relies on simple water level monitoring and timing control. This method cannot respond to dynamic factors such as water quality changes, user needs and equipment status in real time, resulting in low water supply efficiency. In addition, existing monitoring systems often lack effective data analysis and decision support capabilities, making it difficult to achieve refined management and optimized scheduling of equipment.

[0004] Therefore, how to comprehensively monitor and conduct refined analysis of the secondary water supply system, generate appropriate control strategies, realize intelligent control, and improve the water supply efficiency of the secondary water supply system has become an urgent problem to be solved. Summary of the invention

[0005] The present invention provides a secondary water supply intelligent control method and system, which can comprehensively monitor and perform refined analysis on the secondary water supply system, generate appropriate control strategies, realize intelligent control, and improve the water supply efficiency of the secondary water supply system.

[0006] A first aspect of the present invention provides a secondary water supply intelligent control method, comprising: A corresponding twin model is constructed based on the connection relationship of all devices in the secondary water supply system, wherein the twin model includes at least a water tank twin module, a pipeline twin module and an auxiliary equipment twin module, and the twin model is segmented based on the water tank twin module to obtain multiple water supply twin paths; The working status of each twin module in the twin model is obtained to obtain the first status information, and the water quality information and water flow information are detected and processed based on the corresponding multimodal Internet of Things acquisition device in each water tank twin module to obtain multimodal detection information; Inputting the multimodal detection information into a pre-configured control neural network, and sequentially calculating, analyzing and processing based on the neurons in the control neural network to obtain an intelligent control strategy for the secondary water supply system; Based on the intelligent control strategy, the control information of each module in the twin model is generated, and the corresponding physical equipment is controlled.

[0007] Optionally, in a possible implementation manner of the first aspect, the twin model corresponding to the connection relationship of all devices in the secondary water supply system is constructed, and the twin model includes at least a water tank twin module, a pipeline twin module, and an auxiliary equipment twin module. The twin model is segmented based on the water tank twin module to obtain multiple water supply twin paths, including: The model building end interacts with the server to build twin modules of all equipment in the secondary water supply system; The model building end connects all twin modules based on the connection relationship of all equipment in the secondary water supply system to obtain a twin model corresponding to the secondary water supply system; Add corresponding labels to all twin modules in the twin model to obtain a water tank twin module, a pipeline twin module, and an auxiliary equipment twin module, where there are multiple water tank twin modules; Taking the water tank twin module as the segmentation target, the twin model is segmented to obtain multiple water supply twin paths.

[0008] Optionally, in a possible implementation of the first aspect, taking the water tank twin module as the segmentation target, segmenting the twin model to obtain multiple water supply twin paths includes: Determine the twin water outlets and twin water inlets corresponding to the twin modules of the water tank respectively; Taking the twin water inlet of each water tank twin module as the first starting point, sequentially determine other twin modules that are directly and / or indirectly connected toward the municipal water pipeline until the twin module directly connected to the municipal water pipeline is determined, thereby obtaining the first water inlet twin path; Taking the twin water outlet of each water tank twin module as the second starting point, other twin modules that are directly and / or indirectly connected to the user's water pipeline are determined in turn until the twin module directly connected to the user's water pipeline is determined, thereby obtaining the second main water inlet twin path and the second slave water inlet twin path.

[0009] Optionally, in a possible implementation of the first aspect, the method takes the twin water outlet of each water tank twin module as the second starting point, sequentially determines other twin modules that are directly and / or indirectly connected toward the user water pipeline, and stops after the twin module directly connected to the user water pipeline is determined, to obtain the second main water inlet twin path and the second slave water inlet twin path, including: sequentially determine other twin modules that are directly and / or indirectly connected toward the user water pipeline, and when determining a new twin module, obtain the number of the connected new twin modules; If the number of the connected new twin modules is 1, the previously determined twin module connected to a new twin module is judged to be a non-forked module; If the number of the connected new twin modules is greater than 1, the previously determined twin module connected to the multiple new twin modules is judged to be a forked module; Taking each bifurcation module as the starting point again, determine other twin modules that are directly and / or indirectly connected until the twin module directly connected to the user's water pipeline is determined, and then obtain the second main water inlet twin path and the second slave water inlet twin path based on the bifurcation module.

[0010] Optionally, in a possible implementation of the first aspect, the method again takes each bifurcation module as a starting point, determines other twin modules that are directly and / or indirectly connected, and stops after determining the twin module that is directly connected to the user's water pipe, and obtains a second main water inlet twin path and a second slave water inlet twin path based on the bifurcation module, including: Again, taking each bifurcated module as a starting point, determine other twin modules that are directly and / or indirectly connected, until the last other twin module is determined or the user's water pipeline stops determining other twin modules; If it is determined that the last twin module is not connected to the user's water pipeline, the corresponding twin module is used as a non-water supply path twin module; If it is determined that the last twin module is connected to the user's water pipeline, the corresponding twin module is used as the water supply path twin module; Based on the non-water supply path twin module, the water supply path twin module and the bifurcation module, the second main water inlet twin path and the second slave water inlet twin path are obtained.

[0011] Optionally, in a possible implementation of the first aspect, obtaining the second main water inlet twin path and the second slave water inlet twin path based on the non-water supply path twin module, the water supply path twin module and the bifurcation module includes: Count all other twin modules between the twin module of the non-water supply path and the bifurcation module to generate auxiliary equipment paths; Count all modules in the water supply path from the twin module to the bifurcation module and from the bifurcation module to the twin outlet to generate the water inlet twin path; If it is determined that the same bifurcated module is in multiple water inlet twin paths, the path length of each water inlet twin path is obtained, and the path with the shortest length is taken as the second main water inlet twin path, and the other water inlet twin paths other than the second main water inlet twin path are taken as the second slave water inlet twin paths; If it is determined that a user's water pipeline is simultaneously connected to the second main water inlet twin path and the second slave water inlet twin path of different water tank twin modules, the corresponding multiple water tank twin modules will be used as the water supply control group of the user's water pipeline.

[0012] Optionally, in a possible implementation of the first aspect, the method further includes: If the model building end inputs path configuration data, a corresponding first water inlet twin path, a second main water inlet twin path or a second slave water inlet twin path is formed based on the twin module selected in the path configuration data; If the water supply control data is input into the judgment model building end, the user's water pipeline is connected to the corresponding water tank twin module based on the pipeline module added by the water supply control data to obtain a manually updated water supply control group.

[0013] Optionally, in a possible implementation manner of the first aspect, the obtaining of the working state of each twin module in the twin model to obtain first state information, and the detection and processing of water quality information and water flow information by a corresponding multimodal Internet of Things acquisition device in each water tank twin module to obtain multimodal detection information include: Obtaining a water tank working state of a water tank twin module in a twin model, wherein the water tank working state includes being turned on or off; Obtaining a pipeline working state of a pipeline twin module in a twin model, where the pipeline working state includes being opened or not opened; Obtaining the auxiliary working state of the auxiliary device twin module, where the auxiliary working state includes being enabled or disabled; Based on the corresponding multimodal Internet of Things acquisition devices in each water tank twin module, water quality information and water flow information are detected and processed to obtain multimodal detection information under different water tanks.

[0014] Optionally, in a possible implementation of the first aspect, the multimodal detection information is input into a preconfigured control neural network, and neurons in the control neural network are sequentially calculated, analyzed and processed to obtain an intelligent control strategy for the secondary water supply system, including: Constructing a control neural network, wherein the control neural network includes connected classification neurons, input neurons, calculation neurons, and output neurons; Based on the configuration of each neuron in the control neural network, a corresponding control neural network is obtained; Based on the classification neurons, the multimodal detection information is classified and input to the corresponding input neurons. The computing neurons receive the input information of the input neurons connected to them and then calculate and process to obtain the control information. The output neuron determines the twin module and control method to be regulated based on the regulation information, and the intelligent regulation strategy at least includes the twin module and control method to be regulated.

[0015] Optionally, in a possible implementation of the first aspect, obtaining a corresponding regulated neural network based on the configuration of each neuron in the regulated neural network includes: Adding a classification strategy to the classification neuron, the classification strategy is used to classify the input multimodal detection information once according to the water tank twin module in which it is located, and to perform secondary classification according to the detection type of each mode in the multimodal detection information; Construct an input neuron group corresponding to each water tank twin module, construct an input neuron for each type of modal detection information in each input neuron group, and each input neuron is used to input the corresponding modal detection information of the corresponding water tank twin module; Constructing a connection relationship and a calculation strategy between each calculation neuron and an input neuron, wherein the calculation strategy is used to calculate the detection information of the input neuron to obtain the control information; The connection relationship between each output neuron and the computing neuron and the control strategy are constructed so that the output neuron outputs the required regulated twin module and control method after receiving the control information. The control strategy has a corresponding relationship between the control information and the twin module and the control method.

[0016] Optionally, in a possible implementation manner of the first aspect, the step of constructing a connection relationship between each computing neuron and an input neuron and a computing strategy, wherein the computing strategy is used to calculate detection information of the input neuron to obtain regulation information, includes: Constructing a connection relationship and a calculation strategy between each calculation neuron and an input neuron, wherein the calculation strategy includes a strategy mapping table, wherein the strategy mapping table has a strategy interval value of modal detection information of each dimension, and a feedback value corresponding to the corresponding strategy interval value; The calculation strategy includes a feedback value combination table, in which there is control information under different feedback value combinations, and each feedback value combination has control information preset by the water supply control group.

[0017] A second aspect of the present invention provides a secondary water supply intelligent control system, comprising: A construction module, used to construct a corresponding twin model based on the connection relationship of all equipment in the secondary water supply system, wherein the twin model includes at least a water tank twin module, a pipeline twin module and an auxiliary equipment twin module, and the twin model is segmented based on the water tank twin module to obtain multiple water supply twin paths; An acquisition module is used to obtain the working status of each twin module in the twin model to obtain first status information, and to detect and process water quality information and water flow information based on the corresponding multimodal Internet of Things acquisition device in each water tank twin module to obtain multimodal detection information; An analysis module, used for inputting the multimodal detection information into a pre-configured control neural network, and sequentially calculating, analyzing and processing based on neurons in the control neural network to obtain an intelligent control strategy for the secondary water supply system; The control module is used to generate control information for each module in the twin model based on the intelligent control strategy, and perform control processing on the corresponding physical equipment.

[0018] According to a third aspect of the present invention, a storage medium is provided, in which a computer program is stored. When the computer program is executed by a processor, it is used to implement the method of the first aspect of the present invention and various possible designs of the first aspect.

[0019] The beneficial effects of the present invention are as follows: 1. The present invention can comprehensively monitor and conduct refined analysis on the secondary water supply system, generate appropriate control strategies, realize intelligent control, and improve the water supply efficiency of the secondary water supply system. First of all, the present invention effectively integrates the connection relationship between water tanks, pipes and auxiliary equipment by constructing a twin model of the secondary water supply system, forming a comprehensive and systematic management twin model. In addition, the present invention can identify multiple water supply twin paths by segmenting the model, so that the physical equipment can be quickly controlled and processed in combination with the control information. The acquired multimodal detection information can be input into the corresponding control neural network for refined analysis, thereby generating control information adapted to the current water supply system, so as to control the physical equipment and improve the flexibility and efficiency of water supply.

[0020] 2. The present invention can divide the twin model to obtain multiple water supply twin paths, so as to determine the appropriate control strategy in combination with the multimodal detection information collected in real time, realize the flexible scheduling of the water supply path, and thus improve the water supply efficiency of the water supply system. Among them, the present invention can realize the dynamic scheduling of the path during the water supply process by identifying and marking the main and slave water supply paths, ensuring that when one path fails, other paths can replenish water supply in time, thereby improving the water supply reliability of the water supply system. In addition, the present invention can comprehensively analyze a variety of data (such as water quality information and flow information) to improve the accuracy and effectiveness of the control strategy, so that the operation of the water supply system is more scientific and reasonable. Finally, the present invention also supports managers to input path configuration data and water supply control data according to actual needs, and flexibly adjust the water supply path, such as adding new pipelines or equipment to meet the needs of different users and realize personalized water supply services.

[0021] 3. The present invention can construct a control neural network to receive multimodal detection information for intelligent analysis and decision-making, generate specific control strategies, and improve the automation and intelligence level of water supply management. Among them, the present invention can use classification neurons to perform primary and secondary classification on input data to ensure the orderliness and pertinence of information flow, thereby improving the accuracy of data processing, and through real-time calculations based on connected input data by computing neurons, it can quickly respond to changes in system status, generate real-time control information, and improve the response speed of the water supply system. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Figure 1 A flow chart of a secondary water supply intelligent control method provided by the present invention; Figure 2 A schematic diagram of a control neural network provided by the present invention; Figure 3 A structural schematic diagram of a secondary water supply intelligent control system provided by the present invention. DETAILED DESCRIPTION

[0023] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0024] The technical solution of the present invention is described in detail with specific embodiments below. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described in detail in some embodiments.

[0025] like Figure 1 As shown, the present invention provides a flow chart of a secondary water supply intelligent control method, the secondary water supply intelligent control method comprising: S1. Construct a corresponding twin model based on the connection relationship of all equipment in the secondary water supply system. The twin model includes at least a water tank twin module, a pipeline twin module and an auxiliary equipment twin module. The twin model is segmented based on the water tank twin module to obtain multiple water supply twin paths.

[0026] It should be noted that secondary water supply refers to the form in which units or individuals store and pressurize urban public water supply or self-built facilities water supply, and then supply it to users or for their own use through pipelines. Secondary water supply is mainly established to compensate for the lack of pressure in municipal water supply pipelines and to ensure water supply for people living in high-rise buildings. However, when the community uses a lot of water and the water tank storage capacity is small, it is easy to fail to provide users with sufficient water in time. Moreover, when the corresponding community uses less water, the water in the water tank cannot be replaced in time. In order to ensure the safety of water quality supplied to users, it is necessary to regularly clean the water storage equipment, such as regularly cleaning the water tank. Furthermore, during the cleaning of the water tank, the community needs to stop water supply, which will affect the user's water demand. Therefore, a corresponding twin model can be constructed according to the secondary water supply system of the corresponding community in order to determine the corresponding multiple water supply twin paths, so as to perform intelligent regulation according to the multiple water supply twin paths, so as to improve water supply efficiency and reduce the number of water outages.

[0027] It can be understood that the twin model is a virtual digital model corresponding to the secondary water supply system, including a water tank twin module, a pipe twin module and an auxiliary equipment twin module, wherein the water tank twin module is a twin module corresponding to the water tank in the secondary water supply system, the pipe twin module is a twin module corresponding to the pipe for transmitting water sources in the secondary water supply system, and the auxiliary equipment twin module is a twin module of the auxiliary equipment for secondary water supply. For example, the secondary water supply system has auxiliary equipment such as pressure pumps and detection equipment that supply water to high floors, then the corresponding auxiliary equipment twin modules are pressure pump twin modules, detection equipment twin modules, etc.

[0028] Among them, the water supply twin path is a virtual twin path for water supply.

[0029] It is not difficult to understand that in the secondary water supply process, the water stored in the water tank is usually distributed and supplied according to the corresponding water flow path. Therefore, the twin model can be segmented according to the water tank twin module to obtain multiple water supply twin paths, which is convenient for subsequent management and control based on the water supply twin paths, thereby improving the water supply efficiency.

[0030] In some embodiments, the specific implementation of step S1 (the twin model corresponding to the connection relationship of all devices in the secondary water supply system is constructed, the twin model at least includes a water tank twin module, a pipeline twin module and an auxiliary equipment twin module, and the twin model is segmented based on the water tank twin module to obtain multiple water supply twin paths) includes: S11, the model building end interacts with the server to build twin modules of all equipment in the secondary water supply system.

[0031] It can be understood that the model building end exchanges data and transmits commands with the server through a network connection in order to build a twin module of all equipment in the secondary water supply system, thereby facilitating the subsequent acquisition of the twin model corresponding to the secondary water supply system.

[0032] Among them, the model building end is the information terminal of the manager who builds the twin model, such as a computer, mobile phone, etc. The twin module is a virtual digital module of the corresponding equipment in the secondary water supply system, that is, a virtualized system component. Each twin module corresponds to a physical device. The water tank twin module, pipeline twin module and auxiliary equipment twin module respectively represent the water tanks, pipelines and various auxiliary equipment (such as pumps, valves, etc.) in the actual system.

[0033] S12, the model building end connects all twin modules based on the connection relationship of all equipment in the secondary water supply system to obtain a twin model corresponding to the secondary water supply system.

[0034] It can be understood that the connection relationship reflects the physical connection and water flow path between the various devices in the actual water supply system, so that the constructed twin modules can be connected according to the connection relationship to obtain a twin model with a corresponding connection relationship to the actual secondary water supply system.

[0035] Through the above-mentioned implementation mode, the present invention can obtain a twin model corresponding to the actual water supply system, so as to quickly divide it according to the twin model and determine the water supply twin path, so as to facilitate the subsequent intelligent regulation of the water supply system.

[0036] S13, add corresponding labels to all twin modules in the twin model to obtain a water tank twin module, a pipeline twin module and an auxiliary equipment twin module, where there are multiple water tank twin modules.

[0037] It is understandable that a specific label is added to each module in the twin model to make it clear which physical component it represents.

[0038] For example, the module corresponding to the water tank equipment in the actual secondary water supply system is marked as a water tank twin module, which facilitates the identification and distinction of the twin module in subsequent processing.

[0039] S14, taking the water tank twin module as the segmentation target, segmenting the twin model to obtain multiple water supply twin paths.

[0040] It should be noted that when supplying water to users, the water in the corresponding water tank is usually pressed to each user through a pipe. Therefore, in order to regulate the water supply system, the water tank twin module can be used as the basis for path segmentation to obtain multiple water supply twin paths, which is convenient for fine-tuning control and optimizing the operating efficiency of each water supply path.

[0041] Among them, the segmentation target is the target point for dividing the twin model, and the water supply twin path is the virtual path representing the flow of water in the twin model, reflecting the water delivery route from the water source to the user.

[0042] For example, in a high-rise residential community, there are multiple water tanks, complex pipe networks and different auxiliary equipment. The model building end first interacts with the server to obtain detailed information about these devices. Then, based on the actual pipe connections and water flow directions, a comprehensive twin model is built and marked. Finally, with each water tank as the center, the twin model is divided into multiple water supply paths, each path corresponding to a specific floor or area. This division makes subsequent detection and regulation more targeted.

[0043] It is not difficult to understand that clearer equipment marking and path segmentation facilitate equipment management and simplify the complexity of fault diagnosis when a water supply system fails.

[0044] In some embodiments, the specific implementation of step S14 (taking the water tank twin module as the segmentation target and segmenting the twin model to obtain multiple water supply twin paths) includes: S141, respectively determine the twin water outlets and twin water inlets corresponding to the twin modules of the water tank.

[0045] It can be understood that in each water tank twin module, the virtual water outlet and water inlet corresponding to the actual water tank are identified. The location points corresponding to these water outlets and water inlets are the key nodes connecting the water tank with the pipeline network, which determine the path for the water tank to receive and transport water.

[0046] Among them, the twin water outlet is the water outlet corresponding to the twin module of the water tank, and the twin water inlet is the water inlet corresponding to the twin module of the water tank.

[0047] S142, taking the twin water inlet of each water tank twin module as the first starting point, sequentially determine other twin modules that are directly and / or indirectly connected in the direction of the municipal water pipeline, until the twin module directly connected to the municipal water pipeline is determined, thereby obtaining the first water inlet twin path.

[0048] It can be understood that the water inlet of the water tank is the location where water flowing out of the municipal water pipeline enters the water tank. Therefore, the twin water inlet can be used as the first starting point, and other connected twin modules can be determined in the direction of the municipal water pipeline to obtain the first water inlet twin path.

[0049] Among them, the first starting point is the starting confirmation point for determining the first water inlet twin path, that is, the position point of the twin water inlet corresponding to the water tank twin module, the municipal water pipeline is the municipal water supply pipeline, and the first water inlet twin path is the water flow path of the water inlet corresponding to the water tank twin module.

[0050] For example, when the twin water inlet of the water tank twin module A is confirmed in sequence toward the direction of the municipal water pipeline, it is found that the water tank twin module A is connected to the twin module 1, wherein the twin module 1 is connected to the twin module 2, the twin module 2 is connected to the twin module 3, and the twin module 3 is connected to the municipal water pipeline, then the first water inlet twin path is twin module 3-twin module 2-twin module 1-water tank twin module A, wherein the twin module 1, twin module 2 and twin module 3 can be twin modules corresponding to any type of equipment, for example, they can be pipeline twin modules, auxiliary equipment twin modules, etc. This is only used as an example to facilitate understanding of the confirmation method of the first water inlet twin path.

[0051] S143, taking the twin water outlet of each water tank twin module as the second starting point, sequentially determine other twin modules that are directly and / or indirectly connected to the user's water pipeline, until the twin module directly connected to the user's water pipeline is determined, and then stop, to obtain the second main water inlet twin path and the second slave water inlet twin path.

[0052] It should be noted that, since each water tank can supply water to multiple floors through multiple pipes, and each floor can also have multiple water tanks for water supply, for example, water tank A can provide water to users on floors 1-5 and floors 6-10, and water tank B can also provide water to users on floors 1-5 and floors 6-10, but water tank A mainly provides water to users on floors 1-5, and water tank B mainly provides water to users on floors 6-10. When water tank B has an abnormality or insufficient water supply, water tank A can supply water to users on floors 6-10. Conversely, when water tank B is abnormal or insufficient water supply, water tank A can supply water to users on floors 6-10. When A has an abnormality or insufficient water supply, water tank B can supply water to users on the 1st to 5th floors. Therefore, for water tank A, the water flow path to users on the 1st to 5th floors is the main water inlet path, and the water flow path to users on the 6th to 10th floors is the secondary water inlet path. Similarly, for water tank B, the water flow path to users on the 6th to 10th floors is the main water inlet path, and the water flow path to users on the 1st to 5th floors is the secondary water inlet path. Furthermore, the second main water inlet twin path and the second secondary water inlet twin path corresponding to each water tank twin module can be determined according to the connected twin modules.

[0053] It can be understood that the second starting point is to determine the starting position point of the path connecting the user's water pipe, that is, the twin water outlet corresponding to the water tank twin module, the user's water pipe is a water flow pipe that provides water to the user, the second main water inlet twin path is the mainstream water virtual path that preferentially supplies water to the user, and the second slave water inlet twin path is an auxiliary water supply virtual path that provides water to the user.

[0054] Through the above implementation, the water supply path can be clearly divided, which is convenient for monitoring and regulating the water supply system. Moreover, by clarifying the path information, the problem area can be quickly located when a fault occurs, reducing water outage time and maintenance costs. At the same time, it is also convenient for the subsequent rapid optimization and scheduling of water resources, thereby improving the water supply efficiency of the water supply system.

[0055] In some embodiments, the specific implementation of step S143 (taking the twin water outlet of each water tank twin module as the second starting point, sequentially determining other twin modules directly and / or indirectly connected toward the user water pipe, and stopping after determining the twin module directly connected to the user water pipe, to obtain the second main water inlet twin path and the second slave water inlet twin path) includes: S1431, sequentially determine other twin modules that are directly and / or indirectly connected to the user's water pipeline, and when determining a new twin module, obtain the number of the connected new twin modules.

[0056] It can be understood that starting from the twin outlet of the water tank, the twin modules directly or indirectly connected are identified in sequence along the direction of water flow. When each new twin module is identified (including the current twin module of the water tank), the number of the next twin module connected to the module is recorded to determine whether the path has branches.

[0057] S1432: If the number of the newly connected twin modules is 1, it is determined that the previously determined twin module connected to a new twin module is a non-forked module.

[0058] It can be understood that when the number of newly connected twin modules is 1, it means that the corresponding path currently identified has no forks, so the previous twin module connected to it can be marked as a non-forked module, which means that the water flow path does not split at this node.

[0059] Among them, the non-bifurcated module is a module that does not produce path bifurcations, that is, it does not connect multiple twin modules.

[0060] S1433: If the number of the connected new twin modules is greater than 1, the previously determined twin module connected to multiple new twin modules is judged to be a forked module.

[0061] It can be understood that when the number of newly connected twin modules is greater than 1, it means that the water flow path is forked at this point, and thus the previous twin module of this connection is marked as a forked module, because the previous connected twin module is connected to multiple modules, providing a connection point leading to multiple branch paths.

[0062] Among them, the fork module is a module that connects multiple new twin modules, that is, a twin module that provides connection points for multiple branch paths.

[0063] Through the above implementation, the present invention clearly identifies the path bifurcation points in the water supply network, facilitates subsequent path segmentation, and provides an analytical basis for intelligent water supply management.

[0064] S1434, again taking each bifurcation module as the starting point, determine other twin modules that are directly and / or indirectly connected, until the twin module directly connected to the user's water pipeline is determined, and then obtain the second main water inlet twin path and the second slave water inlet twin path based on the bifurcation module.

[0065] It can be understood that a new path extends from the bifurcation module and continues to determine the twin modules that are directly or indirectly connected until a twin module directly connected to the user's water pipeline is found. According to the different characteristics of the path and the position of the bifurcation module, the second main water inlet twin path and the second slave water inlet twin path are finally obtained. The second main water inlet twin path represents the main flow path, and the second slave water inlet twin path can represent a backup or branch path.

[0066] Through the above-mentioned implementation mode, the present invention helps to reasonably allocate and manage water resources in the future by identifying the main and slave paths, thereby ensuring that the stability of water supply is improved when demand fluctuates.

[0067] In some embodiments, the specific implementation of step S1434 (the step of again taking each bifurcated module as the starting point, determining other twin modules directly and / or indirectly connected, and terminating after determining the twin module directly connected to the user's water pipe, and obtaining the second main water inlet twin path and the second slave water inlet twin path based on the bifurcated module) includes: S14341, again taking each bifurcated module as the starting point, determine other twin modules that are directly and / or indirectly connected, until the last other twin module is determined or the user's water pipeline stops determining other twin modules.

[0068] It can be understood that taking each identified bifurcation module as the starting point, the path identification is restarted, and the search for directly and / or indirectly connected twin modules continues along the water flow direction until the last twin module or the user's water pipe is reached, thereby stopping the path identification extension.

[0069] S14342: If it is determined that the last twin module is not connected to the user's water pipeline, the corresponding twin module will be used as a non-water supply path twin module.

[0070] It is understandable that when the last twin module finally determined is not connected to the user's water pipeline, it can be explained that the equipment corresponding to the twin module is not directly involved in the user's water supply. Therefore, the twin module in this case can be marked as a non-water supply twin module, which means that this path may be a backup path or an invalid path, so as to subsequently master the functions of each twin module and generate appropriate control methods based on the actual equipment functions.

[0071] Among them, the non-water supply path twin module is a twin module that is at the end of the path and is not directly connected to the user's water pipeline.

[0072] S14343: If it is determined that the last twin module is connected to the user's water pipeline, the corresponding twin module will be used as the water supply path twin module.

[0073] It can be understood that if the last twin module is connected to the user's water pipeline, the path is regarded as a valid water supply path, and the last twin module determined is marked as a water supply path twin module, indicating that this is a module directly involved in the user's water supply.

[0074] Among them, the water supply path twin module is a twin module in the path that directly supplies water to users.

[0075] Through the above implementation, water supply paths and non-water supply paths are effectively distinguished and marked, so as to improve the accuracy of network analysis.

[0076] S14344, obtain a second main water inlet twin path and a second slave water inlet twin path based on the non-water supply path twin module, the water supply path twin module and the bifurcation module.

[0077] It can be understood that by marking the twin modules of the non-water supply path and the water supply path and combining the information of the bifurcation module, the paths are integrated and classified, and finally the second main water inlet twin path (main water supply path) and the second slave water inlet twin path (backup or secondary path) are determined.

[0078] It is not difficult to understand that identifying the main water supply path facilitates the subsequent optimization of water resource allocation and use and improves the water supply efficiency of the water supply system. At the same time, in the event of system maintenance or failure, critical paths and backup paths can be quickly identified to facilitate rapid response and processing.

[0079] In some embodiments, the specific implementation of step S14344 (obtaining the second main water inlet twin path and the second slave water inlet twin path based on the non-water supply path twin module, the water supply path twin module and the bifurcation module) includes: Count all other twin modules between the twin module of the non-water supply path and the bifurcation module to generate the auxiliary equipment path.

[0080] It can be understood that all twin modules between the non-water supply path twin module and the fork module are identified and counted, and these modules are connected to form an auxiliary equipment path, which is used to identify and manage module paths that are not directly involved in water supply, so as to facilitate the subsequent generation of appropriate water supply control measures.

[0081] Among them, the auxiliary equipment path is a path formed by connecting equipment that provides auxiliary water supply to users.

[0082] Count all modules in the water supply path from the twin module to the bifurcation module and from the bifurcation module to the twin outlet to generate the water inlet twin path.

[0083] It can be understood that in order to clarify the direction and composition of the water supply path, all modules from the water supply path twin module to the bifurcation module, and from the bifurcation module to the twin water outlet can be obtained, and these modules are connected to generate the water inlet twin path.

[0084] Among them, the water inlet twin path is the water flow twin path that provides water to users.

[0085] If it is determined that the same fork module is in multiple water inlet twin paths, the path length of each water inlet twin path is obtained, and the path with the shortest length is taken as the second main water inlet twin path, and the other water inlet twin paths other than the second main water inlet twin path are taken as the second slave water inlet twin path.

[0086] It should be noted that since the same bifurcation module is connected to multiple water inlet twin paths, the path lengths from the bifurcation module to the user pipeline can be different, where the path lengths are long and short. Therefore, when water is supplied, it will preferentially flow into the user's water pipeline through the short path, so that the path with the shortest length can be used as the second main water inlet twin path, and the remaining water inlet twin paths can be used as the second slave water inlet twin path. This facilitates the subsequent water supply, and can provide water to users in a timely manner through the second main water inlet twin path, reducing the consumption of water flow time in the path, thereby improving water supply efficiency.

[0087] It can be understood that the path length is the length distance of the water inlet twin path.

[0088] Through the above implementation, the present invention can accurately identify the primary and secondary water supply paths, so as to improve the water supply efficiency during subsequent water supply scheduling.

[0089] If it is determined that a user's water pipeline is simultaneously connected to the second main water inlet twin path and the second slave water inlet twin path of different water tank twin modules, the corresponding multiple water tank twin modules will be used as the water supply control group of the user's water pipeline.

[0090] It can be understood that when it is determined that the user water pipeline is simultaneously connected to the second main water inlet twin path and the second slave water inlet twin path of different water tank twin modules, the multiple water tank twin modules connected to the same user water pipeline can be used as the water supply control group of the user water pipeline to facilitate subsequent flexible water supply management.

[0091] Among them, the water supply regulation group is a combination of water tank twin modules that can provide mutual regulation for user water supply needs. For example, when there is a problem with water tank A, the corresponding water tank B in the same water supply regulation group can provide water supply to the user corresponding to water tank A to maintain the basic water needs of the corresponding user.

[0092] It is not difficult to understand that by setting up a water supply control group, flexible allocation of multiple water sources can be achieved and the response capacity of the water supply system can be improved.

[0093] It should be noted that since the equipment in the current secondary water supply system may not be sufficient for water regulation, the manager can independently configure the twin model, for example, a new twin module can be added, or multiple twin modules can be selected for connection, so that new equipment can be configured for the actual secondary water supply system according to the autonomously configured path configuration data. For example, by adding new pipes to increase the water flow path, a suitable water supply regulation strategy can be generated later to improve the water supply efficiency. Therefore, in some embodiments, it also includes: A1. If the model building end inputs path configuration data, a corresponding first water inlet twin path, a second main water inlet twin path or a second slave water inlet twin path is formed based on the twin module selected in the path configuration data.

[0094] It can be understood that the path configuration data is data information for configuring the water flow path.

[0095] It is not difficult to understand that by using the twin module selected in the input path configuration data, the first water inlet twin path, the second main water inlet twin path or the second slave water inlet twin path in the system are dynamically generated or adjusted, allowing flexible path adjustment according to actual needs and configuration data, thereby improving the adaptability of the water supply network.

[0096] A2: If the water supply control data is input into the judgment model building end, the user's water pipeline is connected to the corresponding water tank twin module based on the pipeline module added by the water supply control data to obtain a manually updated water supply control group.

[0097] It can be understood that the water supply regulation data is data information that affects the water supply regulation. For example, it can be connecting the user's water pipeline and the water tank twin module C. In this case, a pipeline twin module is added between the user's water pipeline and the water tank twin module C to add a new water flow path.

[0098] It is not difficult to understand that based on the water supply control data, by adding new pipeline modules, connecting the designated water tank twin modules, generating or updating the water supply control group, manual intervention and optimization of the water supply system can be achieved according to actual needs. Through manual updates and dynamic adjustments, the resource utilization efficiency and response speed of the water supply network are improved.

[0099] S2, obtain the working status of each twin module in the twin model to obtain the first status information, and detect and process the water quality information and water flow information based on the corresponding multimodal Internet of Things acquisition device in each water tank twin module to obtain multimodal detection information.

[0100] It is understandable that the working status of each twin module in the twin model (including water tanks, pipelines and auxiliary equipment) can be obtained. These status information helps to monitor the operation of the equipment in real time and provide early warning of potential problems. In addition, the multimodal Internet of Things acquisition devices installed in the water tank twin module can be used to detect water quality and water flow. These devices can include sensors, flow meters and water quality analyzers, etc., which work together to provide comprehensive detection data. Multimodal detection information provides important indicators about water quality safety and water supply capacity, and provides basic data for subsequent control strategies.

[0101] Among them, the first state information is the working state corresponding to the twin module, such as the working state of being turned on or off. The multimodal Internet of Things acquisition device is a device that collects various types of data, such as a data acquisition device that integrates multiple information such as water quality and water flow. The multimodal detection information is the detection information of various influencing factors related to water quality and water flow, such as water quality information, water flow information, etc. All data related to water supply are included.

[0102] In some embodiments, the specific implementation of step S2 (obtaining the working status of each twin module in the twin model to obtain the first status information, and detecting and processing the water quality information and the water flow information based on the corresponding multimodal Internet of Things acquisition device in each water tank twin module to obtain the multimodal detection information) includes: S21, obtaining the water tank working status of the water tank twin module in the twin model, wherein the water tank working status includes being turned on or off.

[0103] It is understandable that the working status of each water tank twin module is detected to determine whether it is currently in the on state, and the working status information is recorded and stored for subsequent analysis and decision-making.

[0104] Among them, the water tank working status is the working status of the water tank twin module corresponding to the actual water tank equipment.

[0105] S22, obtaining the pipeline working status of the pipeline twin module in the twin model, where the pipeline working status includes being opened or not opened.

[0106] It is understandable that the working status of each pipeline twin module is detected to determine whether it is currently turned on, and the status information is collected and saved for reference when an abnormality occurs or adjustment is required.

[0107] Among them, the pipeline working status is the working status of the pipeline twin module corresponding to the actual pipeline equipment.

[0108] S23, obtaining the auxiliary working state of the twin module of the auxiliary device, where the auxiliary working state includes being turned on or off.

[0109] It is understandable that attention is paid to the operating status of the twin modules of auxiliary equipment (such as pumps, valves, etc.), determining whether they are running, and recording and storing the operating status information of these auxiliary equipment for use in system optimization and troubleshooting.

[0110] Among them, the auxiliary working state is the working state of the auxiliary device twin module corresponding to the actual auxiliary device.

[0111] Through the above implementation, the system can accurately grasp the real-time operating status of each module through detailed working status monitoring.

[0112] S24, based on the corresponding multimodal Internet of Things acquisition device in each water tank twin module, the water quality information and water flow information are detected and processed to obtain multimodal detection information under different water tanks.

[0113] It can be understood that the multimodal IoT acquisition equipment in the water tank twin module is used to collect water quality information (such as pH value, nitrite, turbidity, etc.) and water flow information in real time, and the collected multimodal data is preprocessed and analyzed to generate multimodal detection information corresponding to each water tank. The processed multimodal detection information is combined with the working status information of the twin module, stored in the system, and transmitted to the decision module when needed.

[0114] It is not difficult to understand that by combining water quality and water flow information, comprehensive environmental monitoring can be achieved through multimodal IoT devices. Based on real-time status and detection information, the system can quickly detect anomalies and respond, improve overall stability and efficiency, and ensure intelligent management and efficient operation of the system.

[0115] S3, inputting the multimodal detection information into a pre-configured control neural network, and sequentially calculating, analyzing and processing based on the neurons in the control neural network to obtain an intelligent control strategy for the secondary water supply system.

[0116] It is understandable that the multimodal detection information is input into a pre-configured control neural network, which, through complex calculations and analysis of the input data and with the help of its inherent neuronal connections, is able to identify patterns, anomalies and optimization opportunities in system operation. After processing by the neural network, the system generates a set of intelligent control strategies, which are designed to optimize water resource allocation, improve water supply efficiency, reduce energy consumption and ensure water quality safety. The control strategies may include adjusting the operating parameters of the pump, optimizing the cleaning time and frequency of the water tank, and selecting the best water supply path.

[0117] Among them, the control neural network is a pre-set neural network for controlling the water supply system, and the intelligent control strategy is an implementation strategy for intelligent control of the secondary water supply.

[0118] In some embodiments, the specific implementation of step S3 (inputting the multimodal detection information into a preconfigured control neural network, and sequentially calculating, analyzing and processing based on the neurons in the control neural network to obtain an intelligent control strategy for the secondary water supply system) includes: S31, constructing a control neural network, wherein the control neural network includes connected classification neurons, input neurons, calculation neurons and output neurons.

[0119] It is understandable that in order to improve the accuracy of data processing and analysis, Figure 2 As shown, the constructed regulatory neural network may include connected classification neurons, input neurons, computing neurons and output neurons, wherein the classification neuron is single and the other types of neurons may be multiple, and the classification neuron is a neuron that performs data classification on multimodal detection information, the input neuron is a neuron that receives input data, the computing neuron is a neuron that processes computing data, and the output neuron is a neuron that outputs the result.

[0120] Through the above implementation, the present invention can construct a control neural network to subsequently input corresponding multimodal detection data for analysis and calculation to obtain an intelligent control strategy, thereby intelligently controlling the secondary water supply system and improving water supply efficiency.

[0121] S32, based on the configuration of each neuron in the control neural network, a corresponding control neural network is obtained.

[0122] It is understandable that based on the functional requirements of various types of neurons, their parameters are configured and initialized, and the entire network is preliminarily optimized to ensure that it can efficiently process input data.

[0123] In some embodiments, the specific implementation of step S32 (obtaining the corresponding regulated neural network based on the configuration of each neuron in the regulated neural network) includes: S321, adding a classification strategy to the classification neuron, wherein the classification strategy is used to perform a primary classification on the input multimodal detection information according to the water tank twin module in which it is located, and to perform a secondary classification according to the detection type of each mode in the multimodal detection information.

[0124] It can be understood that the input multimodal detection information can be data detected from different water tanks. Therefore, the received multimodal detection information can be classified according to the water tank twin module to which it belongs based on the classification neuron to determine the input neuron group to which the corresponding data belongs. For example, when the data received by the classification neuron comes from the data information corresponding to the water quality in water tank A, the data can be sent to the input neuron group related to water tank A through the classification neuron. When it is determined that the corresponding data belongs to the water quality data corresponding to water tank A, the input neurons in the input neuron group corresponding to water tank A can be further selected through the corresponding multi-second detection information type to achieve secondary classification, so as to determine the accurate input neurons, thereby inputting the corresponding data into the corresponding input neurons, for example, transmitting the corresponding pH value to the input neuron corresponding to the pH value, so as to facilitate the subsequent accuracy calculation of the data.

[0125] Among them, the first classification is the classification of multimodal detection information according to the water tank twin module, and the secondary classification is to classify the data again according to the data type to determine the specific neurons, so that the corresponding data can be sent to the corresponding input neurons in the future, so as to facilitate the subsequent transmission to the computing neurons for data calculation and analysis to obtain control information.

[0126] It is not difficult to understand that classification neurons can carefully classify input information into primary and secondary categories to ensure the orderliness and pertinence of data flow.

[0127] S322, construct an input neuron group corresponding to each water tank twin module, construct an input neuron for each type of modal detection information in each input neuron group, and each input neuron is used to input the corresponding modal detection information of the corresponding water tank twin module.

[0128] It can be understood that each water tank twin module corresponds to an input neuron group, in each input neuron group, a corresponding input neuron is created for each type of modal detection information, and each input neuron is responsible for receiving and processing detection information of a specific modal type.

[0129] Among them, the input neuron group is a combination of input neurons corresponding to the same water tank data.

[0130] It is not difficult to understand that the modular design of the input neuron group allows the detection information of each water tank twin module and modality type to be processed exclusively.

[0131] S323, constructing a connection relationship and a calculation strategy between each calculation neuron and the input neuron, wherein the calculation strategy is used to calculate the detection information of the input neuron to obtain the control information.

[0132] It can be understood that a connection relationship is established between the computing neurons and the input neurons so that the data information received by each computing neuron can be determined based on the connection relationship, which is convenient for the subsequent accuracy calculation of the computing neurons and a computing strategy is set for each computing neuron. The strategy is used to process the detection information from the connected input neurons and generate corresponding control information.

[0133] Among them, the connection relationship is the connection method between different neurons, the calculation strategy is the calculation method corresponding to the connection relationship between different neurons, such as various calculation methods such as sum, difference, etc., and the control information is the instruction information for controlling the water supply system.

[0134] In some embodiments, the specific implementation of step S323 (the construction of a connection relationship between each computing neuron and an input neuron and a computing strategy, the computing strategy being used to calculate the detection information of the input neuron to obtain the regulation information) includes: S3231, constructing a connection relationship and a calculation strategy between each calculation neuron and the input neuron, wherein the calculation strategy includes a strategy mapping table, wherein the strategy mapping table has a strategy interval value of the modal detection information of each dimension, and a feedback value corresponding to the corresponding strategy interval value.

[0135] It can be understood that the connection relationship between each computing neuron and the input neuron is determined, and the connection relationship determines which input information will be passed to a specific computing neuron for processing, and a strategy mapping table is designed for each computing neuron, which contains strategy interval values ​​of modal detection information of different dimensions.

[0136] Among them, the strategy mapping table is a strategy table that reflects the control instructions corresponding to different values. The strategy interval value is the interval value corresponding to the detection information of different dimensions, such as the corresponding PH value in the water quality information, etc. The feedback value is the control feedback value corresponding to the strategy interval value, such as 0, 1, 2, and different feedback values ​​have corresponding control information. For example, when the feedback value is 0, the corresponding control information may be empty, when the feedback value is 1, the corresponding control information may be to turn on the device, and when the feedback value is 2, the corresponding control information may be to turn off the device. The strategy interval value corresponds to the corresponding feedback value one by one.

[0137] Through the above implementation, the neural network can be regulated to refine information processing, that is, the strategy mapping table enables each computing neuron to make corresponding judgments within different detection information intervals, thereby improving the precision of information processing.

[0138] S3232, the calculation strategy includes a feedback value combination table, the feedback value combination table contains control information under different feedback value combinations, and each feedback value combination has control information preset by the water supply control group.

[0139] It can be understood that the feedback combination table is a control information table that combines multiple different feedback values ​​and has corresponding control information, which can be pre-set manually and is used to combine different feedback values ​​to generate comprehensive control information.

[0140] It is not difficult to understand that the table lists possible feedback value combinations, each combination corresponds to the control needs under different scenarios. According to the specific needs of the water supply system and the preset control group strategy, each feedback value combination is mapped to specific control information. This information will guide the system to take corresponding control actions. For example, when the corresponding feedback value is 0, which corresponds to a normal result, the corresponding control information is empty, which means that no equipment or water flow adjustment is required.

[0141] S324, construct the connection relationship and control strategy between each output neuron and the computing neuron, so that the output neuron outputs the required regulated twin module and control method after receiving the control information, and the control strategy has a corresponding relationship between the control information and the twin module and the control method.

[0142] It can be understood that the connection relationship between the output neurons and the computing neurons is constructed, and the output control strategy is set, so that after the output neurons receive the control information, they can accurately output the twin modules that need to be regulated and the control methods, so that the system can perform automatic control and provide water supply efficiency.

[0143] Among them, the control strategy defines the correspondence between the control information and the twin module and the control method, so that when the output neuron receives the control information, it can output the required twin module and control method. The control method is the specific way to adjust the twin module corresponding to the device, which can be to turn the device on or off. For example, the water tank twin module A can be turned off, and the water tank twin module B can be turned on, etc.

[0144] It is not difficult to understand that computational neurons can dynamically generate regulatory information, while output neurons are accurately mapped to specific regulatory behaviors.

[0145] S33, based on the classification neurons, the multimodal detection information is classified and input to the corresponding input neurons, and the computing neurons receive the input information of the input neurons connected to them and then calculate and process to obtain the control information.

[0146] It can be understood that the input multimodal detection information is first classified and processed by classification neurons. Different types of data are assigned to corresponding input neurons, and each input neuron passes the received information to the connected computing neurons. The computing neurons process it according to the configured algorithms and weights to generate specific control information.

[0147] Through the above implementation, the classification neurons intelligently classify the input multimodal detection information to improve the efficiency and accuracy of data processing, and the computing neurons dynamically calculate and process the input information to provide accurate control suggestions.

[0148] S34, the output neuron determines the twin module and control method to be regulated based on the control information, and the intelligent control strategy at least includes the twin module and control method to be regulated.

[0149] It can be understood that the control information generated by the computing neuron is transmitted to the output neuron, and the output neuron determines the twin module that needs to be regulated and the specific control method based on the control information. The intelligent control strategy finally generated includes at least the twin module that needs to be regulated (such as a specific water tank or pipe) and the specific control method (such as opening, closing, adjusting water flow, etc.).

[0150] It is not difficult to understand that the output neuron intelligently generates and outputs specific control strategies based on the analysis results to guide system operation. The neural network model improves the intelligent management capabilities of the secondary water supply system, ensuring that the system can be accurately regulated according to real-time data, thereby improving water supply efficiency and system stability.

[0151] S4, based on the intelligent control strategy, generates control information for each module in the twin model, and performs control processing on the corresponding physical equipment.

[0152] It is understandable that according to the generated intelligent control strategy, the system will generate specific control information for each module in the twin model. This information covers how to adjust equipment parameters, when to perform maintenance, and how to optimize water flow paths, etc., so that through the Internet of Things connection, the control information is transmitted to the actual secondary water supply equipment, guiding it to make corresponding operational adjustments. This closed-loop control mechanism ensures the effective implementation of the strategy and can continuously adjust the strategy based on feedback to adapt to the dynamic changes of the system.

[0153] Among them, the physical equipment is the equipment in the actual water supply system corresponding to each twin module in the twin model, such as pressure pumps, water tanks, etc.

[0154] Through the above implementation methods, the intelligent control method for secondary water supply realizes comprehensive monitoring and optimization of the water supply system. It can not only perceive and analyze the current situation in real time, but also generate and implement effective control information through the control neural network. This method effectively improves the water supply efficiency and ensures the safety of water quality. At the same time, it also reduces the water supply interruption caused by equipment maintenance or water quality problems, so as to improve the user's water experience.

[0155] like Figure 3 As shown, the present invention provides a structural schematic diagram of a secondary water supply intelligent control system, the secondary water supply intelligent control system comprising: A construction module is used to construct a corresponding twin model based on the connection relationship of all equipment in the secondary water supply system. The twin model includes at least a water tank twin module, a pipeline twin module and an auxiliary equipment twin module. The twin model is segmented based on the water tank twin module to obtain multiple water supply twin paths.

[0156] An acquisition module is used to obtain the working status of each twin module in the twin model to obtain the first status information, and to detect and process the water quality information and water flow information based on the corresponding multimodal Internet of Things acquisition device in each water tank twin module to obtain multimodal detection information.

[0157] The analysis module is used to input the multimodal detection information into a pre-configured control neural network, and sequentially calculate, analyze and process the neurons in the control neural network to obtain an intelligent control strategy for the secondary water supply system.

[0158] The control module is used to generate control information for each module in the twin model based on the intelligent control strategy, and perform control processing on the corresponding physical equipment.

[0159] The present invention also provides a storage medium, in which a computer program is stored. When the computer program is executed by a processor, it is used to implement the methods provided by the various embodiments described above.

[0160] Among them, the storage medium can be a computer storage medium or a communication medium. The communication medium includes any medium that facilitates the transmission of a computer program from one place to another. The computer storage medium can be any available medium that can be accessed by a general-purpose or special-purpose computer. For example, the storage medium is coupled to the processor so that the processor can read information from the storage medium and write information to the storage medium. Of course, the storage medium can also be a component of the processor. The processor and the storage medium can be located in an application-specific integrated circuit (Application Specific Integrated Circuits, referred to as: ASIC). In addition, the ASIC can be located in a user device. Of course, the processor and the storage medium can also exist in a communication device as discrete components. The storage medium can be a read-only memory (ROM), a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, and an optical data storage device, etc.

[0161] The present invention also provides a program product, which includes an execution instruction, which is stored in a storage medium. At least one processor of a device can read the execution instruction from the storage medium, and at least one processor executes the execution instruction so that the device implements the methods provided in the above various embodiments.

[0162] In the above-mentioned terminal or server embodiments, it should be understood that the processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), etc. A general-purpose processor may be a microprocessor or any conventional processor. The steps of the method disclosed in the present invention may be directly implemented as being executed by a hardware processor, or may be executed by a combination of hardware and software modules in the processor.

[0163] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. The secondary water supply intelligent control method is characterized by: include: A corresponding twin model is constructed based on the connection relationship of all devices in the secondary water supply system, wherein the twin model includes at least a water tank twin module, a pipeline twin module and an auxiliary equipment twin module, and the twin model is segmented based on the water tank twin module to obtain multiple water supply twin paths; The working status of each twin module in the twin model is obtained to obtain the first status information, and the water quality information and water flow information are detected and processed based on the corresponding multimodal Internet of Things acquisition device in each water tank twin module to obtain multimodal detection information; Inputting the multimodal detection information into a pre-configured control neural network, and sequentially calculating, analyzing and processing based on the neurons in the control neural network to obtain an intelligent control strategy for the secondary water supply system; Based on the intelligent control strategy, the control information of each module in the twin model is generated, and the corresponding physical equipment is controlled.

2. The secondary water supply intelligent control method according to claim 1, characterized in that: The twin model corresponding to the connection relationship of all devices in the secondary water supply system is constructed, and the twin model at least includes a water tank twin module, a pipeline twin module and an auxiliary equipment twin module. The twin model is segmented based on the water tank twin module to obtain multiple water supply twin paths, including: The model building end interacts with the server to build twin modules of all equipment in the secondary water supply system; The model building end connects all twin modules based on the connection relationship of all equipment in the secondary water supply system to obtain a twin model corresponding to the secondary water supply system; Add corresponding labels to all twin modules in the twin model to obtain a water tank twin module, a pipeline twin module, and an auxiliary equipment twin module, where there are multiple water tank twin modules; Taking the water tank twin module as the segmentation target, the twin model is segmented to obtain multiple water supply twin paths.

3. The secondary water supply intelligent control method according to claim 2 is characterized in that: The water tank twin module is used as the segmentation target, and the twin model is segmented to obtain multiple water supply twin paths, including: Determine the twin water outlets and twin water inlets corresponding to the twin modules of the water tank respectively; Taking the twin water inlet of each water tank twin module as the first starting point, sequentially determine other twin modules that are directly and / or indirectly connected toward the municipal water pipeline until the twin module directly connected to the municipal water pipeline is determined, thereby obtaining the first water inlet twin path; Taking the twin water outlet of each water tank twin module as the second starting point, other twin modules that are directly and / or indirectly connected to the user's water pipeline are determined in turn until the twin module directly connected to the user's water pipeline is determined, thereby obtaining the second main water inlet twin path and the second slave water inlet twin path.

4. The secondary water supply intelligent control method according to claim 3 is characterized in that: The method takes the twin water outlet of each water tank twin module as the second starting point, sequentially determines other twin modules that are directly and / or indirectly connected to the user water pipeline, and stops after the twin module directly connected to the user water pipeline is determined, to obtain the second main water inlet twin path and the second slave water inlet twin path, including: sequentially determine other twin modules that are directly and / or indirectly connected toward the user water pipeline, and when determining a new twin module, obtain the number of the connected new twin modules; If the number of the connected new twin modules is 1, the previously determined twin module connected to a new twin module is judged to be a non-forked module; If the number of the connected new twin modules is greater than 1, the previously determined twin module connected to the multiple new twin modules is judged to be a forked module; Taking each bifurcation module as the starting point again, determine other twin modules that are directly and / or indirectly connected until the twin module directly connected to the user's water pipeline is determined, and then obtain the second main water inlet twin path and the second slave water inlet twin path based on the bifurcation module.

5. The secondary water supply intelligent control method according to claim 4 is characterized in that: The method again takes each bifurcation module as a starting point, determines other twin modules that are directly and / or indirectly connected, and stops after determining the twin module that is directly connected to the user's water pipe, and obtains the second main water inlet twin path and the second slave water inlet twin path based on the bifurcation module, including: Again, taking each bifurcated module as a starting point, determine other twin modules that are directly and / or indirectly connected, until the last other twin module is determined or the user's water pipeline stops determining other twin modules; If it is determined that the last twin module is not connected to the user's water pipeline, the corresponding twin module is used as a non-water supply path twin module; If it is determined that the last twin module is connected to the user's water pipeline, the corresponding twin module is used as the water supply path twin module; Based on the non-water supply path twin module, the water supply path twin module and the bifurcation module, the second main water inlet twin path and the second slave water inlet twin path are obtained.

6. The secondary water supply intelligent control method according to claim 5, characterized in that: The method of obtaining a second main water inlet twin path and a second slave water inlet twin path based on the non-water supply path twin module, the water supply path twin module and the bifurcation module includes: Count all other twin modules between the twin module of the non-water supply path and the bifurcation module to generate auxiliary equipment paths; Count all modules in the water supply path from the twin module to the bifurcation module and from the bifurcation module to the twin outlet to generate the water inlet twin path; If it is determined that the same bifurcated module is in multiple water inlet twin paths, the path length of each water inlet twin path is obtained, and the path with the shortest length is taken as the second main water inlet twin path, and the other water inlet twin paths other than the second main water inlet twin path are taken as the second slave water inlet twin paths; If it is determined that a user's water pipeline is simultaneously connected to the second main water inlet twin path and the second slave water inlet twin path of different water tank twin modules, the corresponding multiple water tank twin modules will be used as the water supply control group of the user's water pipeline.

7. The secondary water supply intelligent control method according to claim 6, characterized in that: Also includes: If the model building end inputs path configuration data, a corresponding first water inlet twin path, a second main water inlet twin path or a second slave water inlet twin path is formed based on the twin module selected in the path configuration data; If the water supply control data is input into the judgment model building end, the user's water pipeline is connected to the corresponding water tank twin module based on the pipeline module added by the water supply control data to obtain a manually updated water supply control group.

8. The secondary water supply intelligent control method according to claim 1, characterized in that: The first state information is obtained by obtaining the working state of each twin module in the twin model, and the multimodal detection information is obtained by detecting and processing the water quality information and the water flow information based on the corresponding multimodal Internet of Things acquisition device in each water tank twin module, including: Obtaining a water tank working state of a water tank twin module in a twin model, wherein the water tank working state includes being turned on or off; Obtaining a pipeline working state of a pipeline twin module in a twin model, where the pipeline working state includes being opened or not opened; Obtaining the auxiliary working state of the auxiliary device twin module, where the auxiliary working state includes being enabled or disabled; Based on the corresponding multimodal Internet of Things acquisition devices in each water tank twin module, water quality information and water flow information are detected and processed to obtain multimodal detection information under different water tanks.

9. The secondary water supply intelligent control method according to claim 7, characterized in that: The multimodal detection information is input into a pre-configured control neural network, and neurons in the control neural network are sequentially calculated, analyzed and processed to obtain an intelligent control strategy for the secondary water supply system, including: Constructing a control neural network, wherein the control neural network includes connected classification neurons, input neurons, calculation neurons, and output neurons; Based on the configuration of each neuron in the control neural network, a corresponding control neural network is obtained; Based on the classification neurons, the multimodal detection information is classified and input to the corresponding input neurons. The computing neurons receive the input information of the input neurons connected to them and then calculate and process to obtain the control information. The output neuron determines the twin module and control method to be regulated based on the regulation information, and the intelligent regulation strategy at least includes the twin module and control method to be regulated.

10. The secondary water supply intelligent control method according to claim 9, characterized in that: The configuration of each neuron in the control neural network is based on obtaining a corresponding control neural network, including: Adding a classification strategy to the classification neuron, the classification strategy is used to classify the input multimodal detection information once according to the water tank twin module in which it is located, and to perform secondary classification according to the detection type of each mode in the multimodal detection information; Construct an input neuron group corresponding to each water tank twin module, construct an input neuron for each type of modal detection information in each input neuron group, and each input neuron is used to input the corresponding modal detection information of the corresponding water tank twin module; Constructing a connection relationship and a calculation strategy between each calculation neuron and an input neuron, wherein the calculation strategy is used to calculate the detection information of the input neuron to obtain the control information; The connection relationship between each output neuron and the computing neuron and the control strategy are constructed so that the output neuron outputs the required regulated twin module and control method after receiving the control information. The control strategy has a corresponding relationship between the control information and the twin module and the control method.

11. The secondary water supply intelligent control method according to claim 10, characterized in that: The construction of the connection relationship between each computing neuron and the input neuron and the computing strategy, wherein the computing strategy is used to calculate the detection information of the input neuron to obtain the control information, includes: Constructing a connection relationship and a calculation strategy between each calculation neuron and an input neuron, wherein the calculation strategy includes a strategy mapping table, wherein the strategy mapping table has a strategy interval value of modal detection information of each dimension, and a feedback value corresponding to the corresponding strategy interval value; The calculation strategy includes a feedback value combination table, in which there is control information under different feedback value combinations, and each feedback value combination has control information preset by the water supply control group.

12. Secondary water supply intelligent control system, characterized in that: include: A construction module, used to construct a corresponding twin model based on the connection relationship of all equipment in the secondary water supply system, wherein the twin model includes at least a water tank twin module, a pipeline twin module and an auxiliary equipment twin module, and the twin model is segmented based on the water tank twin module to obtain multiple water supply twin paths; An acquisition module is used to obtain the working status of each twin module in the twin model to obtain first status information, and to detect and process water quality information and water flow information based on the corresponding multimodal Internet of Things acquisition device in each water tank twin module to obtain multimodal detection information; An analysis module, used for inputting the multimodal detection information into a pre-configured control neural network, and sequentially calculating, analyzing and processing based on neurons in the control neural network to obtain an intelligent control strategy for the secondary water supply system; The control module is used to generate control information for each module in the twin model based on the intelligent control strategy, and perform control processing on the corresponding physical equipment.

Images