Intelligent pipe network pressure reducing system based on model predictive control

Abstract

This invention provides an intelligent pipeline pressure reduction system based on model predictive control, relating to the field of water supply network pressure regulation technology. The method includes: the system comprises execution, hardware control, data acquisition, and wireless transmission modules; the execution components include a pressure reducing valve and a pilot valve; the hardware control unit integrates a model predictive control module and a Kalman filter-based tracking control module; the data acquisition unit collects pressure data and transmits it wirelessly to the control unit; the dual modules calculate and generate control commands to drive the execution components; the system is configured with a cloud-edge-device three-layer architecture and also includes a multi-power supply unit, supporting both distributed and integrated deployments in pits and wells, and achieving bidirectional communication and parameter collaborative optimization with the cloud computing platform. This invention achieves precise closed-loop regulation of pipeline pressure, adapts to multiple deployment scenarios and power supply requirements, improves the real-time performance and system adaptability of regulation, realizes refined intelligent management of the pipeline network, and reduces pipeline operation risks and energy consumption.

Description

Technical Field

[0001] This invention relates to the field of water supply network pressure regulation technology, and in particular to an intelligent network pressure reduction system based on model predictive control. Background Technology

[0002] In the field of urban and rural water supply network operation and management, network pressure regulation is a core element in ensuring the stable and efficient operation of the water supply system. Traditional water supply network pressure regulation often relies on manual on-site adjustment and fixed pressure-reducing valves. These methods are no longer suitable for the operational needs of modern water supply systems. The manual regulation mode depends on staff conducting on-site inspections and adjusting valve openings based on experience. This not only consumes a lot of manpower and time but also suffers from regulation lag, failing to respond quickly to real-time changes in network pressure. This can easily lead to excessively high or low pressure in certain areas of the network, affecting the overall stability of the water supply.

[0003] While fixed pressure-reducing valves can achieve basic pressure reduction, they can only regulate pressure according to a preset value. They cannot dynamically adjust pressure parameters based on the actual water supply load and usage periods of the pipeline network. When the pipeline network is under low water load, fixed pressure reduction can lead to excess pressure, increasing the risk of pipeline leakage and pipe bursts. Conversely, under high water load, insufficient pressure can easily occur, failing to meet the normal water demand of remote users. Furthermore, traditional pressure control systems often use a single algorithm for data processing, which is ineffective at filtering out interference noise during pressure acquisition, resulting in insufficient accuracy of measured pressure data. This further reduces the precision of pressure control, making it difficult to achieve accurate management of pipeline pressure.

[0004] The existing hardware architecture of water supply network pressure control systems is relatively simple, lacking flexible deployment methods. Some systems only support centralized installation, making them unsuitable for outdoor deployment scenarios with long pipelines and dispersed monitoring points. Meanwhile, some distributed deployment systems suffer from poor communication and coordination among components, resulting in low efficiency in data transmission and command issuance. Furthermore, traditional systems are mostly powered by a single mains power source, which is difficult to reliably supply to pipeline nodes without mains coverage. Power outages can easily cause the control system to stop operating, making 24-hour continuous pressure control impossible. Simultaneously, the control and data management ends of existing systems lack effective coordination, only capable of local pressure data processing and control. They cannot achieve global analysis of pipeline pressure data or dynamic optimization of control parameters, hindering the comprehensive and intelligent management of the water supply network and failing to effectively balance the relationship between water supply demand, network safety, and energy consumption control. Summary of the Invention

[0005] To address the technical problems of existing water supply network pressure regulation, such as poor real-time performance, low regulation accuracy, single deployment and power supply modes that are difficult to adapt to outdoor distributed scenarios, lack of global collaborative optimization capabilities, inability to achieve refined and intelligent management, easy to cause network leakage and high risk of pipe bursts, high water supply energy consumption and insufficient water supply stability, this invention provides an intelligent network pressure reduction system based on model predictive control.

[0006] The technical solution provided by this invention is as follows: This invention provides an intelligent pipeline pressure reduction system based on model predictive control, comprising: The system comprises an actuator, a hardware control unit, a data acquisition unit, and a wireless transmission module. The actuator includes a pressure reducing valve as the main valve and a pilot valve as the pilot valve. The data acquisition unit is used to collect pressure data from the water supply network. The hardware control unit integrates a model predictive control module and a tracking control module. The tracking control module employs a Kalman filter algorithm. The data acquisition unit transmits the collected pressure data to the hardware control unit via the wireless transmission module. The model predictive control module combines the pressure data to generate a target setpoint for the network pressure. The tracking control module tracks the measured pressure value and calculates its deviation from the target setpoint. The hardware control unit issues control commands to the pilot valve and the pressure reducing valve based on the deviation.

[0007] Furthermore, the hardware control unit includes a main controller and an auxiliary controller. The main controller is communicatively connected to the auxiliary controller, the wireless transmission module, the data acquisition unit, and the execution component. The auxiliary controller works in concert with the main controller to jointly complete pressure data processing and issue control commands.

[0008] Furthermore, a multi-power supply unit is electrically connected to the hardware control unit, wireless transmission module, data acquisition unit, and execution components to provide power support for each component of the system.

[0009] Furthermore, the multi-power supply unit includes at least two of the following: mains power supply module, solar power supply module, storage battery power supply module, and dry cell battery power supply module, and the power supply can be switched between the power supply modules.

[0010] Furthermore, the battery box, in which the battery of the battery power supply module is integrated, is electrically connected to the hardware control unit, forming the system's backup power supply unit.

[0011] Furthermore, the system adopts a pit-well distributed deployment structure, with the pressure reducing valve and pilot valve being installed separately in the pits or wells of the water supply network. The hardware control unit achieves remote data interaction and control with the distributed pressure reducing valve and pilot valve through a wireless transmission module.

[0012] Furthermore, the system adopts an integrated deployment structure, in which the pressure reducing valve, pilot valve, hardware control unit, data acquisition unit and wireless transmission module are integrated and installed in the same protection unit, adapting to the deployment environment of outdoor water supply networks.

[0013] Furthermore, the hardware control unit achieves variable pressure water supply control through the collaborative work of the model prediction control module and the tracking control module. The variable pressure water supply control includes a variable pressure boosting mode and a variable pressure depressurization mode.

[0014] Furthermore, the system is configured with a three-layer functional architecture of cloud-edge-device. The terminal is an instrument and control terminal consisting of a data acquisition unit and an execution component. The edge layer is a hardware control unit, and the cloud is a cloud computing platform. The three interact with each other through a wireless transmission module to achieve intelligent control of the water supply network pressure. The hardware control unit establishes bidirectional communication with the cloud computing platform through the wireless transmission module, uploads network pressure data and system operation status data to the cloud computing platform, and receives pressure control parameters issued by the cloud computing platform.

[0015] Furthermore, based on the uploaded pressure data and operating status data, the cloud computing platform collaborates with the model predictive control module of the hardware control unit to optimize the pressure regulation parameters, and then sends the optimized regulation parameters to the hardware control unit through a wireless transmission module to achieve dynamic optimization and regulation of the water supply network pressure.

[0016] The beneficial effects of the technical solution provided by this invention include at least the following: (1) In this invention, the model prediction control module and the tracking control module using the Kalman filter algorithm work together to accurately process and calculate the deviation of the measured pressure data of the water supply network, effectively filter out the interference noise in the data acquisition process, improve the accuracy of the pressure data, and combine the cloud-edge-end three-layer architecture to realize the real-time transmission of pressure data and the rapid issuance of control commands, replacing the traditional manual control and fixed pressure reduction method, realizing the dynamic and accurate closed-loop control of the network pressure, solving the problems of poor real-time performance and low accuracy of the traditional control method, effectively avoiding the situation of excessively high or low network pressure, and improving the overall water supply stability.

[0017] (2) In this invention, two deployment structures are designed: a distributed pit and a unified integrated structure. The two structures can be flexibly selected according to the layout characteristics of the water supply network and adapted to different network renovation and construction scenarios. At the same time, a multi-power supply unit including mains power, solar energy, storage battery and dry battery is configured to support multi-mode power supply switching. This solves the problem of single deployment and power supply mode in traditional systems. Even in distributed network nodes without mains power coverage outdoors, a stable and continuous power supply can be achieved, ensuring the system operates 24 hours a day without interruption, and greatly improving the system's environmental adaptability and operational stability.

[0018] (3) In this invention, the hardware control unit and the cloud computing platform are communicated bidirectionally through the wireless transmission module. The cloud computing platform can perform global analysis on the pipeline pressure data and system operation status data, and work with the model prediction control module of the hardware control unit to optimize the pressure regulation parameters. This realizes the global management of pipeline pressure data and the dynamic optimization of regulation parameters, replacing the local single control mode of the traditional system. It realizes the refined and intelligent management of the water supply network. The variable pressure water supply control mode balances the pipeline pressure under different water loads, effectively reduces pipeline leakage and the risk of pipe bursts, and at the same time reduces the energy consumption of the water supply system and extends the service life of the pipeline and supporting infrastructure. Attached Figure Description

[0019] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0020] Figure 1 This is a schematic diagram of the cloud-edge-end architecture of an intelligent pipeline pressure reduction system based on model predictive control, provided as an embodiment of the present invention. Detailed Implementation

[0021] This invention provides an intelligent pipeline pressure reduction system based on model predictive control, which may include: The system comprises an actuator, a hardware control unit, a data acquisition unit, and a wireless transmission module. The actuator includes a pressure reducing valve (as the main valve) and a pilot valve (as the pilot valve). The data acquisition unit collects pressure data from the water supply network. The hardware control unit integrates a model predictive control module and a tracking control module. The tracking control module employs a Kalman filter algorithm. The data acquisition unit transmits the collected pressure data to the hardware control unit via the wireless transmission module. The model predictive control module combines the pressure data to generate a target setpoint for the network pressure. The tracking control module tracks the measured pressure value and calculates its deviation from the target setpoint. The hardware control unit issues control commands to the pilot valve and the pressure reducing valve based on the deviation.

[0022] Specifically, the actuator serves as the execution end for pipeline pressure regulation. The pressure reducing valve and the pilot valve are connected in series to the section of the water supply network to be regulated. The two work together in a coordinated manner. The regulation commands issued by the hardware control unit can directly drive the pilot valve and the pressure reducing valve to adjust the valve opening, thereby achieving precise regulation of water pressure in the water supply network. The data acquisition unit is deployed at the pressure monitoring nodes of the water supply network. It can collect pipeline pressure data in real time and complete preliminary signal processing. Then, it transmits the data to the hardware control unit through the wireless transmission module. As the core control component of the system, the hardware control unit receives the pressure data and completes data calculation and deviation calculation through the built-in dual algorithm module to generate regulation commands, which are finally sent to the actuator to complete the pressure regulation.

[0023] It should be noted that the hardware control unit includes a main controller and an auxiliary controller. The main controller communicates with the auxiliary controller, the wireless transmission module, the data acquisition unit, and the execution components. The auxiliary controller works in concert with the main controller to process pressure data and issue control commands. The main controller is the core processing module of the hardware control unit, responsible for receiving, processing, and generating various types of data and commands. It establishes direct communication connections with the auxiliary controller, wireless transmission module, data acquisition unit, and execution components to ensure real-time data transmission and command issuance. The auxiliary controller, as an auxiliary processing module, works in concert with the main controller. It can share the computational load when the main controller is under heavy data processing, and it can also perform data verification after the main controller completes basic calculations. Together, they complete the entire process of pressure data processing and accurately issue control commands, ensuring the stability and accuracy of system control.

[0024] In one possible implementation, the intelligent pipeline pressure reduction system also includes a multi-power supply unit. This multi-power supply unit is electrically connected to the hardware control unit, wireless transmission module, data acquisition unit, and execution components, providing power support to all components of the system. Specifically, the multi-power supply unit provides a continuous and stable power supply to all electrical components of the system. It establishes direct electrical connections with the hardware control unit, wireless transmission module, data acquisition unit, and execution components, and can match the corresponding power supply according to the power requirements of each component, ensuring that all components can operate normally and efficiently. This adapts to outdoor, distributed deployment scenarios of water supply networks and solves the power supply problems of different monitoring nodes.

[0025] It should be noted that the multi-power supply unit includes at least two of the following: mains power supply module, solar power supply module, battery power supply module, and dry cell battery power supply module. These power supply modules can switch between each other. It is understood that the multi-power supply unit is not a single power supply mode, but rather includes at least two of the four power supply modules: mains power, solar power, battery, and dry cell battery. Each power supply module is equipped with an automatic switching switch, which can intelligently switch according to the actual deployment environment and power supply conditions. For example, at pipeline nodes with mains power coverage, the mains power supply module can be used as the primary power supply mode; at pipeline nodes outdoors without mains power coverage, the solar power supply module can be used as the primary power supply mode. Switching between power supply modules requires no manual intervention; the system can automatically identify the power supply status and complete the switching, ensuring continuous power supply.

[0026] In one possible implementation, the intelligent pipeline pressure reduction system also includes a battery box. The battery of the battery power supply module is integrated into the battery box, which is electrically connected to the hardware control unit, forming a backup power supply unit for the system. Specifically, the core component of the battery power supply module, the battery, is integrated into the battery box. The battery box protects the battery and simultaneously enables electrical connection between the battery and the hardware control unit. This integrated battery power supply module serves as a backup power supply unit for the system. When the main power supply modules, such as mains power or solar power, experience interruptions or malfunctions, it can automatically be activated to supply power to the hardware control unit and the core components of the system, preventing system shutdown due to power outages and ensuring the system's continuous operation capability.

[0027] It should be noted that the system adopts a pit-and-well distributed deployment structure. Pressure reducing valves and pilot valves are installed separately within the pits or wells of the water supply network. The hardware control unit achieves remote data interaction and control with the distributed pressure reducing valves and pilot valves via a wireless transmission module. Specifically, the pit-and-well distributed deployment structure is suitable for application scenarios with long water supply network lines and dispersed monitoring points. The pressure reducing valves and pilot valves, the actuators, are installed nearby within the pits or wells of the water supply network and directly connected to the network sections. The hardware control unit can be centrally deployed at the network's monitoring station or nearby protective facilities, without needing to be installed at the same location as the pressure reducing valves and pilot valves. The hardware control unit establishes a remote communication connection with the pressure reducing valves and pilot valves distributed in each pit and well via a wireless transmission module, enabling remote interaction of pressure regulation data and remote issuance of control commands, thus achieving remote intelligent control of the network pressure.

[0028] In one possible implementation, the system adopts an integrated deployment structure, with the pressure reducing valve, pilot valve, hardware control unit, data acquisition unit, and wireless transmission module integrated into the same protective unit, adaptable to the deployment environment of outdoor water supply networks. It is understood that the integrated deployment structure is suitable for application scenarios such as newly built water supply networks and key control nodes in the network. By integrating all the core components of the system—the pressure reducing valve, pilot valve, hardware control unit, data acquisition unit, and wireless transmission module—into a single protective unit, this unit possesses waterproof, dustproof, impact-resistant, and corrosion-resistant characteristics, allowing direct deployment in various environments of outdoor water supply networks. The integrated design reduces on-site installation and commissioning procedures, while the close connection of each component improves the efficiency of data transmission and command issuance, ensuring the system's operational stability.

[0029] It should be noted that the hardware control unit achieves variable pressure water supply control through the collaborative work of the model predictive control module and the tracking control module. Variable pressure water supply control includes variable pressure boosting mode and variable pressure depressurization mode. Specifically, the core regulation function of the hardware control unit is achieved collaboratively by the model predictive control module and the tracking control module. These two modules work together to complete real-time monitoring and dynamic regulation of the pipeline pressure, thereby realizing the system's variable pressure water supply control. This variable pressure water supply control includes two modes: variable pressure boosting and variable pressure depressurization. It can automatically switch according to the real-time pressure of the water supply network and water supply demand. When the pipeline pressure is too high, the system activates the variable pressure depressurization mode; when the pipeline pressure is too low, the system activates the variable pressure boosting mode. The switching between the two modes is automatically determined by the hardware control unit based on the pressure data uploaded by the data acquisition unit, without manual operation.

[0030] In one possible implementation, the system is configured with a three-layer cloud-edge-device architecture. The device is a control unit consisting of a data acquisition unit and execution components. The edge layer is a hardware control unit, and the cloud is a cloud computing platform. These three layers interact via a wireless transmission module to achieve intelligent control of the water supply network pressure. The hardware control unit establishes bidirectional communication with the cloud computing platform through the wireless transmission module, uploading network pressure data and system operating status data to the cloud computing platform, and receiving pressure control parameters from the cloud computing platform. It is understood that the stable bidirectional communication connection between the hardware control unit and the cloud computing platform allows the hardware control unit to continuously upload real-time collected network pressure data and operating status data of various system components to the cloud computing platform, providing raw data for data analysis and parameter optimization. Simultaneously, the hardware control unit receives pressure control parameters from the cloud computing platform in real time, adjusting the target setpoint of the network pressure based on the optimized parameters to achieve dynamic optimization of pressure control. This bidirectional communication mode ensures the synergy of the cloud-edge-device three-layer architecture. Meanwhile, the cloud-edge-device three-layer functional architecture realizes full-process data interaction through wireless transmission modules. The terminal layer only completes basic instrumentation and control operations, the edge layer undertakes core control and computing functions, and the cloud layer realizes data storage, analysis and optimization. The three-layer architecture works together to realize intelligent regulation of pipeline pressure.

[0031] It should be noted that the cloud computing platform, based on uploaded pressure and operational status data, collaborates with the model predictive control module of the hardware control unit to optimize pressure regulation parameters. The optimized parameters are then transmitted wirelessly to the hardware control unit, enabling dynamic optimization and regulation of the water supply network pressure. Specifically, after receiving network pressure and system operational status data uploaded by the hardware control unit, the cloud computing platform utilizes big data computing capabilities to perform in-depth analysis. Combining historical network operational data and global water supply demand, it performs preliminary optimization of pressure regulation parameters. Simultaneously, the cloud computing platform establishes a collaborative optimization relationship with the model predictive control module of the hardware control unit, sending the preliminarily optimized parameters to the model predictive control module. The model predictive control module then performs secondary verification and optimization of the parameters based on real-time network pressure data. Finally, the cloud computing platform transmits the collaboratively optimized pressure regulation parameters wirelessly to the hardware control unit. The hardware control unit updates the network pressure target setpoint based on the new regulation parameters, thereby achieving dynamic optimization and regulation of the water supply network pressure. This enables precise and intelligent management of network pressure, effectively reducing network leakage, saving water supply energy, and extending the service life of network assets.

[0032] The beneficial effects of the technical solutions provided in the embodiments of the present invention include at least the following: (1) In this invention, the model prediction control module and the tracking control module using the Kalman filter algorithm work together to accurately process and calculate the deviation of the measured pressure data of the water supply network, effectively filter out the interference noise in the data acquisition process, improve the accuracy of the pressure data, and combine the cloud-edge-end three-layer architecture to realize the real-time transmission of pressure data and the rapid issuance of control commands, replacing the traditional manual control and fixed pressure reduction method, realizing the dynamic and accurate closed-loop control of the network pressure, solving the problems of poor real-time performance and low accuracy of the traditional control method, effectively avoiding the situation of excessively high or low network pressure, and improving the overall water supply stability.

[0033] (2) In this invention, two deployment structures are designed: a distributed pit and a unified integrated structure. The two structures can be flexibly selected according to the layout characteristics of the water supply network and adapted to different network renovation and construction scenarios. At the same time, a multi-power supply unit including mains power, solar energy, storage battery and dry battery is configured to support multi-mode power supply switching. This solves the problem of single deployment and power supply mode in traditional systems. Even in distributed network nodes without mains power coverage outdoors, a stable and continuous power supply can be achieved, ensuring the system operates 24 hours a day without interruption, and greatly improving the system's environmental adaptability and operational stability.

[0034] (3) In this invention, the hardware control unit and the cloud computing platform are communicated bidirectionally through the wireless transmission module. The cloud computing platform can perform global analysis on the pipeline pressure data and system operation status data, and work with the model prediction control module of the hardware control unit to optimize the pressure regulation parameters. This realizes the global management of pipeline pressure data and the dynamic optimization of regulation parameters, replacing the local single control mode of the traditional system. It realizes the refined and intelligent management of the water supply network. The variable pressure water supply control mode balances the pipeline pressure under different water loads, effectively reduces pipeline leakage and the risk of pipe bursts, and at the same time reduces the energy consumption of the water supply system and extends the service life of the pipeline and supporting infrastructure.

[0035] The above are merely specific embodiments of the present invention, but the scope of protection of the present invention is not limited thereto. The scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A smart pipeline pressure reduction system based on model predictive control, characterized in that, include: The system comprises an actuator, a hardware control unit, a data acquisition unit, and a wireless transmission module. The actuator includes a pressure reducing valve as the main valve and a pilot valve as the pilot valve. The data acquisition unit is used to collect pressure data from the water supply network. The hardware control unit integrates a model predictive control module and a tracking control module. The tracking control module employs a Kalman filter algorithm. The data acquisition unit transmits the collected pressure data to the hardware control unit via the wireless transmission module. The model predictive control module combines the pressure data to generate a target setpoint for the network pressure. The tracking control module tracks the measured pressure value and calculates its deviation from the target setpoint. The hardware control unit issues control commands to the pilot valve and the pressure reducing valve based on the deviation. The system is configured with a three-layer functional architecture of cloud-edge-device. The terminal is an instrument and control terminal consisting of a data acquisition unit and an execution component. The edge layer is a hardware control unit, and the cloud is a cloud computing platform. The three interact with each other through a wireless transmission module to achieve intelligent control of the water supply network pressure. The hardware control unit establishes bidirectional communication with the cloud computing platform through the wireless transmission module, uploads network pressure data and system operation status data to the cloud computing platform, and receives pressure control parameters issued by the cloud computing platform. The cloud computing platform, based on the uploaded pressure data and operating status data, works in collaboration with the model predictive control module of the hardware control unit to optimize pressure regulation parameters, and then sends the optimized regulation parameters to the hardware control unit via a wireless transmission module, thereby realizing dynamic optimization and regulation of water supply network pressure.

2. The intelligent pipeline pressure reduction system based on model predictive control according to claim 1, characterized in that, include: The hardware control unit includes a main controller and an auxiliary controller. The main controller is communicatively connected to the auxiliary controller, the wireless transmission module, the data acquisition unit, and the execution component. The auxiliary controller works in concert with the main controller to jointly complete pressure data processing and issue control commands.

3. The intelligent pipeline pressure reduction system based on model predictive control according to claim 1, characterized in that, include: The multi-power supply unit is electrically connected to the hardware control unit, wireless transmission module, data acquisition unit and execution components, providing power support for each component of the system.

4. The intelligent pipeline pressure reduction system based on model predictive control according to claim 3, characterized in that, include: The multi-power supply unit includes at least two of the following: mains power supply module, solar power supply module, storage battery power supply module, and dry cell battery power supply module, and the power supply can be switched between the power supply modules.

5. The intelligent pipeline pressure reduction system based on model predictive control according to claim 4, characterized in that, include: The battery box integrates the battery of the battery power supply module. The battery box is electrically connected to the hardware control unit and constitutes the backup power supply unit of the system.

6. The intelligent pipeline pressure reduction system based on model predictive control according to claim 1, characterized in that, include: The system adopts a pit-well distributed deployment structure. The pressure reducing valves and pilot valves are installed separately in the pits or wells of the water supply network. The hardware control unit realizes remote data interaction and control with the distributed pressure reducing valves and pilot valves through a wireless transmission module.

7. The intelligent pipeline pressure reduction system based on model predictive control according to claim 1, characterized in that, include: The system adopts an integrated deployment structure, in which the pressure reducing valve, pilot valve, hardware control unit, data acquisition unit and wireless transmission module are integrated and installed in the same protection unit, which is suitable for the deployment environment of outdoor water supply network.

8. The intelligent pipeline pressure reduction system based on model predictive control according to claim 1, characterized in that, include: The hardware control unit achieves variable pressure water supply control through the collaborative work of the model prediction control module and the tracking control module. The variable pressure water supply control includes a variable pressure boosting mode and a variable pressure depressurization mode.

Images