Intelligent control and gas supply distribution methods and systems for compressed air systems in nuclear facilities

Abstract

This invention relates to the field of intelligent control technology for compressed air systems, and discloses an intelligent control and gas supply distribution method and system for the compressed air system pipeline network of a nuclear facility. The method includes: constructing a simulation model of the compressed air pipeline network system, and numerically simulating the flow and pressure characteristics of the compressed air pipeline network under different air compressor station distributions, operating conditions, and intermittent loads of different process equipment; based on the data generated by the numerical simulation, using an intelligent fuzzy self-tuning PID control method to adjust the pressure at the end of the compressed air pipeline network system, and optimizing the operating status of the air compressor units in the compressed air pipeline network system based on a flow matching strategy; and real-time acquisition of the pipeline network operating parameters and feedback to adjust the control strategy. Overall, this method can achieve efficient and stable operation of the compressed air system, ensuring the compressed air needs of all aspects of the nuclear facility, while improving the intelligence and reliability of system operation and reducing the adverse effects caused by pressure instability and other problems.

Description

Technical Field

[0001] This invention relates to the field of intelligent control technology for compressed air systems, specifically to an intelligent control and gas supply distribution method and system for a compressed air system network in a nuclear facility. Background Technology

[0002] As a critical plant-wide reprocessing system in nuclear power plants, the compressed air system plays a core role in supplying compressed air power to the nuclear island, conventional island, and BOP (Balance of Plant) sub-projects, covering all operating conditions including normal operation, accident response, commissioning, and maintenance. Although the system itself does not directly perform safety functions, it needs to provide compressed air power support for instrumentation in some safety-level systems to perform safety functions during accident conditions. Therefore, it must have sufficient air supply capacity and stable and reliable operating performance to ensure continuous air supply during accidents, while also meeting the design requirements of energy conservation, environmental protection, and advanced and reasonable technical solutions.

[0003] Currently, nuclear power plant compressed air systems face three major technical challenges: firstly, the overall system air supply volume is large; secondly, the proportion of intermittent loads is high; and thirdly, the timing and pattern of intermittent compressed air usage are uncertain. A sudden surge in intermittent air demand within a short period can trigger a dual risk: firstly, a significant drop in system pipeline pressure can directly impact the normal operation of safety-grade air-consuming equipment, potentially leading to process interruptions; secondly, emergency air compressors may enter a dormant state due to accidental start / stop triggering, failing to start normally in the event of a real accident, severely threatening the safety functions of the entire plant. Furthermore, critical process air-consuming equipment such as air lifters and compressed air jet pumps have extremely high requirements for the stability of air supply pressure and flow rate. If parameter fluctuations exceed allowable ranges, equipment efficiency will significantly decrease, or even completely cease operation. Summary of the Invention

[0004] In view of this, and in response to the above-mentioned technical problems, embodiments of the present invention provide an intelligent control and gas supply distribution method and system for the compressed air system network of nuclear facilities. By deeply analyzing the operating characteristics of the compressed air system and various operating conditions under intermittent load loading, focusing on the degree of impact on safety-level equipment and the pressure fluctuation law of the safety-level compressed air system network, effective predictive control technology and intelligent gas supply distribution technology are established to form a complete safe gas supply guarantee system, ultimately achieving stable and efficient operation of the compressed air system and providing support for the safe and stable operation of nuclear power plants.

[0005] In a first aspect, the present invention provides an intelligent control and gas supply distribution method for a nuclear facility compressed air system network, the method comprising:

[0006] A simulation model of the compressed air pipeline network system was constructed to numerically simulate the flow and pressure characteristics of the compressed air pipeline network under different air compressor station distribution settings, operating conditions, and intermittent loads of different process equipment.

[0007] Based on the data generated by numerical simulation, control measures are taken for various operating conditions in the compressed air system based on predictive control strategies, including: using intelligent fuzzy self-tuning PID control method to adjust the pressure at the end of the compressed air pipeline network, and optimizing the operating status of the air compressor units in the compressed air pipeline network based on flow matching strategies.

[0008] Real-time acquisition of pipeline operation parameters of the compressed air pipeline system and feedback to adjust control strategies.

[0009] The intelligent control and gas supply distribution method for the compressed air system network of nuclear facilities provided in this invention, by constructing a simulation model of the compressed air network system, can accurately simulate the flow and pressure characteristics of the compressed air network under different scenarios, providing a reliable data foundation for subsequent control strategy formulation. Employing an intelligent fuzzy self-tuning PID control method, the pressure at the end of the network can be flexibly and accurately adjusted to cope with pressure fluctuations under complex operating conditions. Optimizing the operating state of the air compressor unit based on a flow matching strategy allows the unit operation to better match actual gas demand. Combined with real-time parameter acquisition and feedback adjustment of the control strategy, a closed-loop control is formed, enabling efficient and stable operation of the compressed air system, ensuring the compressed air needs of all aspects of the nuclear facility, while improving the intelligence and reliability of system operation and reducing adverse effects caused by pressure instability.

[0010] In one optional implementation, when constructing the compressed air pipeline system simulation model, one-dimensional thermofluid simulation software is used. The modeling content includes the selection of compressed air pipeline system components, topology construction, and boundary condition setting. Components include straight pipes, bends, tees, valves, air compressor stations, and user terminals. After modeling is completed, model debugging and verification are performed to ensure that the model error is within a preset range. Model debugging and verification include:

[0011] Design variable definition: Pipe diameter, valve opening, and resistance component parameters in the pipeline network are used as adjustable design variables, wherein the design variables include continuous variables, discrete variables, or combinations thereof;

[0012] Constraint settings: Establish constraints including pressure fluctuation range, flow supply capacity, and pipeline structure limitations to ensure that the optimization results are within the engineering feasibility range;

[0013] Objective function construction: The expected flow matching degree of each branch in the pipeline network is taken as the main optimization objective, while energy consumption minimization and gas supply stability indicators are also considered.

[0014] Iterative optimization: An analysis-driven optimization framework is adopted. Through fluid network simulation and iterative calculation of optimization algorithms, in each iteration, the flow characteristics of the pipeline network are analyzed based on the current design variable values ​​to obtain pressure distribution and flow distribution data. The degree of satisfaction of the objective function is evaluated by the optimization algorithm and a new combination of design variables is generated. The above process is repeated until the convergence condition is met or the maximum number of iterations is reached to obtain the optimal pipeline network configuration scheme.

[0015] In constructing the simulation model of the compressed air pipeline system, this invention utilizes one-dimensional thermofluid simulation software to comprehensively model various pipeline components, ensuring a high degree of fidelity to the actual pipeline network. By defining design variables, setting constraints, constructing objective functions, and iteratively optimizing, the optimal pipeline configuration scheme that achieves high flow matching between pipeline branches, low energy consumption, and stable gas supply can be found within the scope of engineering feasibility. This helps optimize the pipeline structure from the source, laying the foundation for stable operation and efficient gas supply of the subsequent compressed air system, reducing problems such as pressure fluctuations and uneven flow distribution caused by pipeline factors, and improving the overall system performance.

[0016] In one optional implementation, the numerical simulation includes steady-state simulation, transient simulation, and configuration optimization analysis; wherein:

[0017] Steady-state simulation is used to simulate the changes in branch pipe pressure drop, main pipe pressure drop, and flow rate impact when different users experience sudden intermittent load increases, clarifying the coupling effect of user location and load increment on system pressure;

[0018] Transient simulation is used to simulate the dynamic pressure response characteristics of the system under sudden intermittent load increases, including the pressure drop rate, the impact of air compressor start-up time and number on pressure recovery time, and the critical pressure value under multi-user coordinated load.

[0019] Configuration optimization analysis focuses on the distribution of air compressor stations, pipeline network scale, pressure stabilizing tank volume, and air compressor start-up and shutdown strategies to determine the optimal configuration parameters.

[0020] This invention subdivides numerical simulation into steady-state simulation, transient simulation, and configuration optimization analysis. Steady-state simulation clearly reveals the impact of sudden intermittent load surges on branch and main pipe pressure drops and flow rates, clarifying the pressure coupling effect between user location and load increment. Transient simulation accurately controls the dynamic response of system pressure during sudden intermittent load surges, including the pressure drop rate, the impact of compressor start-up and shutdown on pressure recovery, and the critical pressure for multi-user coordinated loads. Configuration optimization analysis determines optimal configuration parameters based on key factors such as compressor station distribution and pipeline network scale. This multi-dimensional simulation analysis provides comprehensive and accurate data for the design and operation strategy formulation of compressed air systems, helping to optimize compressor station layout and pipeline network scale, improve the system's ability to cope with various load changes, and ensure gas supply stability.

[0021] In one optional implementation, the method of adjusting the pressure at the end of the compressed air pipeline network using intelligent fuzzy self-tuning PID control includes:

[0022] The pressure deviation and deviation change rate at the end of the compressed air pipeline are used as inputs to the fuzzy controller, and the proportional coefficient correction value, integral coefficient correction value, and derivative coefficient correction value of the PID controller are used as outputs. The online tuning of the input-output relationship is established through fuzzy mathematical reasoning to control the pressure fluctuation at the end of the pipeline within the preset range.

[0023] This invention employs an intelligent fuzzy self-tuning PID control method to regulate the pressure at the end of the pipeline network. The pressure deviation and deviation change rate are taken as inputs, and the PID parameter correction values ​​are outputs. Parameters are tuned online through fuzzy mathematical inference. Compared to traditional PID control, this method can more flexibly adapt to the nonlinear and time-varying characteristics of compressed air systems, quickly and accurately controlling pressure fluctuations at the end of the pipeline network within a preset range. It effectively prevents excessive pressure fluctuations from affecting the normal operation of safety-grade equipment or critical process equipment, ensuring the stability of the compressed air power source and improving the intelligence and accuracy of the system's pressure control.

[0024] In one optional implementation, the optimization of the air compressor unit operating status of the compressed air pipeline network system based on the flow matching strategy includes:

[0025] The compressed air system's air supply network is equivalent to a closed container with an effective volume. The air compressor supplying air to the network is equivalent to isothermally filling the closed container with air, and the air used by the production equipment at the end of the network is equivalent to isothermally releasing air from the closed container.

[0026] The system detects the real-time pressure and flow rate at each end of the pipeline network, senses changes in the gas load at the end based on the real-time pressure and flow rate, and predicts the total compressed air demand flow rate of the pipeline network.

[0027] Based on the predicted total demand flow, combined with the flow matching strategy, the parameters of each air compressor, and the preset operating rules, the air compressor operating strategy is adjusted to maintain the relatively stable pressure of the compressed air system pipeline network, thereby obtaining the optimized operating state of the air compressor unit.

[0028] This invention optimizes the operating status of air compressor units based on a flow matching strategy. By treating the pipeline network as a closed container, and the air supply from the air compressor and the air consumption of the equipment as equivalent to the inflation and deflation processes, the invention combines real-time pressure and flow data at the terminal to sense load changes and predict total demand flow. Then, the unit operation is adjusted according to the flow matching strategy. This ensures a high degree of matching between the air compressor unit's operating status and actual air demand, avoiding unnecessary start-ups, shutdowns, or inefficient operation. It guarantees relatively stable pipeline pressure, meets the air requirements of various equipment, improves unit operating efficiency, saves energy, and reduces pressure fluctuations caused by mismatches between unit operation and demand.

[0029] In an optional implementation, the method further includes:

[0030] The flow characteristics of the compressed air pipeline network are calculated by establishing the mass-energy conservation equation of the nodes and the momentum conservation equation of the components. The variables to be solved include the flow rate at each port of the components, the temperature and pressure of the nodes.

[0031] A system of nonlinear equations is constructed, with the number of equations matching the number of variables to be solved. The Newton-Raphson method is used to iteratively solve the system to obtain the parameters at each location in the pipeline network, providing data support for numerical simulation and control strategy formulation.

[0032] This invention calculates pipeline flow characteristics by establishing nodal mass-energy conservation equations and component momentum conservation equations, and uses the Newton-Raphson method iteratively to obtain parameters at various locations within the pipeline network. This provides accurate data support for numerical simulation and control strategy formulation. This data allows numerical simulations to better reflect actual pipeline flow conditions, enabling control strategies to be formulated based on accurate pipeline characteristics, thereby improving the accuracy and effectiveness of control. It also helps to more accurately grasp the distribution and changes of parameters such as pressure, flow rate, and temperature within the pipeline network, providing a crucial data foundation for optimizing compressed air system operation and ensuring stable gas supply, thus enhancing the scientific rigor and reliability of system operation.

[0033] Secondly, the present invention provides an intelligent control and gas supply distribution system for a nuclear facility compressed air system network, the system comprising:

[0034] The numerical simulation module is used to build a simulation model of the compressed air pipeline system and to perform numerical simulations of the flow and pressure characteristics of the compressed air pipeline under different air compressor station distribution settings, operating conditions, and intermittent loads of different process equipment.

[0035] The intelligent control and air supply distribution module is used to take control measures for various operating conditions in the compressed air system based on data generated by numerical simulation and predictive control strategies. These measures include: using intelligent fuzzy self-tuning PID control to adjust the pressure at the end of the compressed air pipeline network, and optimizing the operating status of the air compressor units in the compressed air pipeline network based on flow matching strategies.

[0036] The communication module allows users to collect real-time pipeline operation parameters of the compressed air pipeline system and provide feedback to adjust control strategies.

[0037] In one alternative implementation, the system further includes:

[0038] The compressed air system pipeline modeling interface module comprises three sub-modules: a component library, a canvas, and an output interface. The component library pre-stores the main component types required for the compressed air system pipeline, including at least straight pipes, bends, tees, and valves. The canvas serves as a configurable operation area for building the pipeline model, allowing users to construct a graphical model of the compressed air system pipeline by dragging and dropping components and connecting component ports. The output interface converts the graphical compressed air system pipeline model into an input card file recognizable by the compressed air system pipeline flow characteristic calculation program. The compressed air system operation status monitoring interface module dynamically displays the operating parameters of the main equipment in the compressed air system. These operating parameters include at least pressure and flow parameters within the compressed air system pipeline, providing a real-time view of the compressed air system's operating status.

[0039] The compressed air pipeline flow characteristic calculation module is used to calculate the flow characteristics of the compressed air pipeline by establishing the mass-energy conservation equations of nodes and the momentum conservation equations of components. The variables to be solved include the flow rate at each port of the component, the temperature and pressure of the node, etc. A set of nonlinear equations is constructed, with the number of equations being the same as the number of variables to be solved. The Newton-Raphson method is used to iteratively solve the equations to obtain the parameters at each location of the pipeline, providing data support for numerical simulation and control strategy formulation.

[0040] The compressed air system operation status database module is used to store pipeline flow and pressure characteristic data calculated by simulation and optimization methods, as well as pipeline operation data collected by the acquisition interface. The equipment control module is used to convert control commands of each device into control current.

[0041] The compressed air system pipeline network modeling interface module of this invention uses three sub-modules—a component library, a canvas, and an output interface—to work together. The component library pre-stores core components such as straight pipes to meet the basic requirements of pipeline network modeling. The canvas supports configurable drag-and-drop connections, reducing the difficulty of user modeling operations and improving the efficiency and intuitiveness of model building. The output interface automatically converts the graphical model into a calculation program input card file, avoiding manual conversion errors and ensuring smooth connection between the model and the calculation process. The compressed air system operation status monitoring interface module dynamically displays key parameters such as pressure and flow rate, helping users to grasp the system operation status in real time, promptly detect parameter anomalies, and provide intuitive basis for operation and maintenance decisions. The compressed air pipeline network flow characteristic calculation module is based on the nodal mass-energy conservation and component momentum conservation equations, combined with the Newton-Raphson method for iterative solution, to accurately obtain parameters at various locations in the pipeline network, providing reliable data support for numerical simulation and control strategy formulation, ensuring that the simulation results are close to reality and the control strategies are scientific and reasonable, effectively ensuring the stable and efficient operation of the compressed air system.

[0042] Thirdly, the present invention provides a computer device, comprising: a memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the computer instructions to perform the intelligent control and gas supply distribution method for the nuclear facility compressed air system network described in the first aspect or any corresponding embodiment thereof.

[0043] Fourthly, the present invention provides a computer-readable storage medium storing computer instructions for causing a computer to execute the intelligent control and gas supply distribution method for the nuclear facility compressed air system network of the first aspect or any corresponding embodiment described above.

[0044] Fifthly, the present invention provides a computer program product, including computer instructions, which are used to cause a computer to execute the intelligent control and gas supply distribution method for the nuclear facility compressed air system network of the first aspect or any corresponding embodiment described above. Attached Figure Description

[0045] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0046] Figure 1 This is a flowchart illustrating the intelligent control and gas supply distribution method for the compressed air system network of a nuclear facility according to an embodiment of the present invention.

[0047] Figure 2 This is a Flomaster simulation model for steady-state simulation of compressed air system pipeline networks according to an embodiment of the present invention;

[0048] Figure 3 This is a Flomaster simulation model for transient simulation of compressed air system pipeline networks according to an embodiment of the present invention;

[0049] Figure 4 This is a structural diagram of an intelligent fuzzy self-tuning PID control system according to an embodiment of the present invention;

[0050] Figure 5 This is a Simulink simulation model of an intelligent fuzzy self-tuning PID control system according to an embodiment of the present invention;

[0051] Figure 6 These are simulation results of end-point pressure according to embodiments of the present invention;

[0052] Figure 7 This is a flowchart of a flow matching control strategy based on the terminal according to an embodiment of the present invention;

[0053] Figure 8 This is a structural block diagram of an intelligent control and gas supply distribution system for a nuclear facility compressed air system network according to an embodiment of the present invention.

[0054] Figure 9 This is a schematic diagram of the hardware structure of a computer device according to an embodiment of the present invention. Detailed Implementation

[0055] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0056] This invention provides an embodiment of an intelligent control and gas supply distribution method for a nuclear facility compressed air system pipeline network. Figure 1 This is a flowchart of an intelligent control and gas supply distribution method for a nuclear facility compressed air system network according to an embodiment of the present invention. It should be noted that the steps shown in the flowchart can be executed in a computer device such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that presented here. Figure 1 As shown, the process includes the following steps:

[0057] Step S101: Construct a simulation model of the compressed air pipeline system and perform numerical simulations on the flow and pressure characteristics of the compressed air pipeline under different air compressor station distribution settings, operating conditions, and intermittent loads of different process equipment.

[0058] This invention employs the professional one-dimensional thermo-fluid simulation software Flomaster to study flow and pressure characteristics, establishing a simulation model of the compressed air pipeline system. The modeling includes component selection, topology construction, and boundary condition setting. Components include straight pipes, bends, tees, valves, air compressor stations, and user terminals. After modeling, model debugging and verification are performed to ensure model errors are within a preset range. Model debugging and verification include:

[0059] 1. Design Variable Definition: Pipe diameter, valve opening, and resistance component parameters in the pipeline network are defined as adjustable design variables. These design variables include continuous variables, discrete variables, or combinations thereof. This invention explicitly defines pipe diameter, valve opening, and resistance component parameters as adjustable design variables, covering continuous variables, discrete variables, and combinations thereof, comprehensively encompassing key parameter dimensions for pipeline network optimization. This allows for fine-tuning of continuously changing parameters such as pipe diameter, while also adapting to the actual engineering needs of discrete parameters such as valve opening levels and resistance component models. This avoids optimization blind spots caused by incomplete variable definitions, laying a parameter foundation for subsequent precise optimization and ensuring that the optimization direction highly aligns with the actual operation and control needs of the pipeline network.

[0060] 2. Constraint Setting: Constraints including pressure fluctuation range, flow supply capacity, and pipeline structure limitations are established to ensure that the optimization results remain within the engineering feasibility range. This embodiment of the invention defines the optimization boundary from both core performance and physical structure dimensions by establishing three types of constraints: pressure fluctuation range, flow supply capacity, and pipeline structure limitations. On the one hand, the pressure fluctuation range constraint directly matches the stringent requirements of nuclear facility safety-grade equipment for gas supply pressure stability, preventing the optimization results from affecting safety functions due to pressure deviations. On the other hand, the flow supply capacity constraint ensures that the optimized scheme meets the gas demand of various process equipment, while the pipeline structure limitation adapts to the existing space and pipeline layout of the plant, effectively avoiding the problem of "theoretically optimal but engineering infeasible," and ensuring that the optimized scheme can be implemented.

[0061] 3. Objective Function Construction: The expected flow matching degree of each branch in the pipeline network is used as the main optimization objective, while also considering energy consumption minimization and gas supply stability indicators. This embodiment of the invention uses the expected flow matching degree of each branch in the pipeline network as the core objective, taking into account both energy consumption and gas supply stability, achieving a triple optimization objective of "supply and demand matching + energy saving + safety". Prioritizing flow matching degree ensures that each user end accurately obtains the required flow, avoiding equipment efficiency decline caused by localized excess or insufficient flow; minimizing energy consumption reduces the operating energy consumption of air compressor units, meeting the environmental protection and energy-saving requirements of nuclear facilities; and the gas supply stability indicator further strengthens the system's resistance to load fluctuations. The synergy of these three aspects allows the optimization scheme to achieve a balance between economy and reliability while meeting functional requirements, improving the overall operating efficiency of the system.

[0062] 4. Iterative optimization: An analysis-driven optimization framework is adopted. Through fluid network simulation and iterative calculation of optimization algorithms, in each iteration, the flow characteristics of the pipeline network are analyzed based on the current design variable values ​​to obtain pressure distribution and flow distribution data. The degree of satisfaction of the objective function is evaluated by the optimization algorithm and a new combination of design variables is generated. The above process is repeated until the convergence condition is met or the maximum number of iterations is reached to obtain the optimal pipeline network configuration scheme.

[0063] This invention employs an analysis-driven optimization framework. Through fluid network simulation and iterative calculations of optimization algorithms, a closed-loop optimization process of "simulation analysis - result evaluation - parameter adjustment" can be achieved. Each iteration performs flow characteristic analysis based on the current design variables, enabling real-time acquisition of key data such as pressure distribution and flow allocation, providing accurate feedback for the optimization algorithm. By continuously evaluating the degree of objective function satisfaction and updating variable combinations, the optimal solution can be gradually approximated. Furthermore, the setting of convergence conditions and the maximum number of iterations can control computational costs while ensuring optimization accuracy, efficiently obtaining the optimal pipeline network configuration scheme. Compared with traditional trial calculation methods, this significantly improves optimization efficiency and scheme reliability, providing the optimal initial configuration for the subsequent stable operation of the compressed air system.

[0064] Furthermore, based on the constructed model, typical operating condition calculations are performed, calculation results are processed and analyzed, intelligent gas supply distribution data interfaces are customized, and analysis report content is compiled. For example... Figure 2 and Figure 3 As shown, a simulation model of the compressed air pipeline system was established in Flomaster software, and numerical simulation analysis was performed for typical operating conditions, including:

[0065] 1. Steady-state simulation, used to simulate the changes in branch pipe pressure drop, main pipe pressure drop, and flow rate impact during sudden increases in intermittent loads for different users, clarifying the coupling effect of user location and load increment on system pressure, including:

[0066] (1) Pressure distribution characteristics analysis: For example, when the intermittent load of users 3, 4 and 5 suddenly increases, the pressure drop of the branch pipe increases significantly. Among them, user 5 has the greatest impact on the outlet pressure of the air compressor station (pressure drop reaches 0.10665 bar). User 6 has the highest pressure drop because it is farthest from the air compressor station and has the smallest pipe diameter (0.15255255 bar under continuous operation).

[0067] (2) Traffic impact analysis: For example, user 5 has the largest intermittent load increment (65N). This resulted in the most significant increase in the main pipe pressure drop, verifying the coupling effect of user location and load increment on system pressure.

[0068] By identifying key users and pressure coupling patterns through steady-state simulation, precise targeting can be provided for pipeline network design. For example, branch pipe diameters can be optimized and gas supply paths can be shortened for highly sensitive users, reducing the risk of pressure drop during sudden load increases from the source. This ensures the pressure stability of safety-grade gas-using equipment and important process equipment (such as air lifters and compressed air jet pumps), avoiding equipment efficiency reduction or process interruption due to sudden pressure drops, and laying a solid foundation for the steady-state operation of the compressed air system.

[0069] 2. Transient simulation, used to simulate the dynamic pressure response characteristics of the system under sudden increases in intermittent load, including the pressure drop rate, the impact of air compressor start-up time and number on pressure recovery time, and the critical pressure value under multi-user coordinated load, including:

[0070] (1) Pressure dynamic response: When the intermittent load suddenly increases, the system pressure decreases linearly. The greater the load, the higher the pressure drop rate (e.g., the pressure drop rate reaches -0.048 bar / s at a 2.0 ratio). The start-up time and number of air compressors directly affect the pressure recovery effect. Starting a second air compressor can significantly shorten the recovery time (e.g., the recovery time is reduced from 89s to 49.71s under a 1.5 ratio).

[0071] (2) Critical operating conditions: For example, when users 3+4+5 are simultaneously under intermittent load, the outlet pressure of the air compressor station drops to a minimum of 9.38 barA, and the multi-user coordinated load needs to be controlled first.

[0072] This invention's transient simulation focuses on the dynamic response characteristics of the system during intermittent load surges. It quantifies the pressure drop rate and the impact of air compressor start-up and shutdown parameters on pressure recovery, and identifies critical pressure values ​​under multi-user coordinated loads, effectively filling the dynamic risk blind spots that steady-state simulations cannot cover. Based on the accurate data obtained from the simulation, on the one hand, differentiated air compressor start-up and shutdown strategies can be formulated (such as pre-setting the number of start-ups based on load ratios) to prevent emergency air compressors from entering a dormant state due to erroneous start-up and shutdown, ensuring start-up reliability under accident conditions. On the other hand, it can clearly define the critical pressure threshold for multi-user coordinated loads, set pressure warning lines in advance, and trigger predictive control measures (such as starting standby air compressors in advance) when the system approaches the critical value, preventing the pressure from continuously dropping beyond the allowable range of safety-level equipment. This significantly improves the compressed air system's ability to cope with dynamic load fluctuations and ensures safe gas supply under nuclear facility accident conditions.

[0073] 3. Configuration optimization analysis, focusing on the distribution of air compressor stations, pipeline network scale, pressure stabilizing tank volume, and air compressor start-up and shutdown strategies, is used to determine the optimal configuration parameters. Specifically:

[0074] (1) Distribution of air compressor stations: The coordinated supply of air by two air compressor stations can reduce pressure fluctuations (the pressure at the user end is restored to 9.4~9.49 barA), which is better than the supply of air by a single station.

[0075] (2) Pipeline scale: Increasing the pipeline length will slow down the rate of pressure drop, but will prolong the recovery time (the recovery time increases to 143s at 1.5 times the length).

[0076] (3) Pressure stabilizing tank volume: Increasing the storage tank can buffer pressure fluctuations ( The storage tank reduces the pressure drop rate by 30%, but slows down the recovery rate.

[0077] (4) Air compressor start-up and shutdown strategy: Shortening the start-up time (10s) can increase the minimum pressure to 7.92 barA, and optimizing the start-up and shutdown logic can balance efficiency and stability.

[0078] The configuration optimization analysis in this invention focuses on four core elements: air compressor station distribution, pipeline network scale, pressure stabilizing tank volume, and air compressor start-up and shutdown strategy. The aim is to find the optimal configuration scheme feasible for engineering projects through parameter optimization, achieving the dual goals of "stable gas supply + energy efficiency." The optimization results can directly guide engineering design: in terms of air compressor station layout, dual-station collaboration reduces pressure drop at the pipeline end; in pipeline network scale design, the relationship between length and pressure recovery time is balanced; when selecting pressure stabilizing tanks, the optimal volume is determined based on pressure drop control requirements; in terms of air compressor start-up and shutdown logic, start-up time and frequency are optimized to balance stability and energy consumption. The resulting optimal configuration scheme reduces pipeline pressure fluctuations, improves gas supply stability, and avoids energy waste caused by redundant equipment operation, meeting the design requirements of "stable, reliable, energy-saving, and environmentally friendly" for nuclear facility compressed air systems, and providing feasible parameter basis for subsequent engineering applications.

[0079] Step S102: Based on the data generated by numerical simulation, control measures are taken for various operating conditions in the compressed air system based on the predictive control strategy, including: adjusting the pressure at the end of the compressed air pipeline network using an intelligent fuzzy self-tuning PID control method, and optimizing the operating status of the air compressor units in the compressed air pipeline network based on the flow matching strategy.

[0080] This invention employs an intelligent fuzzy self-tuning PID control method to regulate the pressure at the end of the compressed air pipeline system, such as... Figure 4 As shown, the pressure deviation e and the rate of change of deviation ec at the end of the compressed air pipeline network are used as inputs to the fuzzy controller, and the proportional coefficient correction value Δ of the PID controller is used as the input. K p Δ, the correction value of the integral coefficient K i and the differential coefficient correction value Δ K d As output, online tuning is achieved by establishing the input-output relationship through fuzzy mathematical reasoning, controlling the pressure fluctuation at the end of the pipeline network within a preset range. In this way, the controller obtains a suitable K based on the real-time changes in the pressure deviation e and the rate of change of deviation ec at the end of the compressed air pipeline network for different systems. p K i K dThis allows the fuzzy controller to output corresponding control parameters to the controlled object, thereby enhancing its dynamic and static performance, as well as its accuracy, flexibility, and adaptability. For example, when a sudden large intermittent load at the user end causes a pressure drop, the fuzzy controller can quickly adjust the PID parameters to accelerate pressure recovery and prevent the pressure from continuously falling below the safe threshold. Combined with the pipeline end pressure control requirements in the document, this method can effectively resist various disturbances in complex gas usage scenarios, ensuring that the end pressure remains stable within the preset range, providing reliable control support for continuous gas supply under all operating conditions of nuclear facilities (normal operation, commissioning, maintenance, and repair).

[0081] like Figure 5 As shown, a simulation model of the intelligent fuzzy self-tuning PID control system was built in Simulink software. The terminal pressure reduction control system was then simulated, with the given pressure set to 800 kPa. The simulation results of the terminal pressure reduction control system are shown below. Figure 6 As shown, the overshoot is less than 2.5%, indicating good control performance.

[0082] This invention, based on a flow matching strategy and the parameters and operating rules of each air compressor, can achieve an optimized operating state for the air compressor unit. The centrifugal air compressor operates in a constant pressure mode, which can be continuously adjusted by regulating the guide vanes (IGV) and the vent valve (BOV). The screw air compressor operates in a loading and unloading mode, and the start-stop frequency can be reduced by setting appropriate loading and unloading pressure bands. Specifically, optimizing the operating state of the air compressor unit in the compressed air pipeline system based on the flow matching strategy includes:

[0083] 1. The compressed air supply network is equivalent to a closed container with an effective volume. The air compressor supplying air to the network is equivalent to isothermal filling of the closed container, and the air used by the production equipment at the end of the network is equivalent to isothermal venting from the closed container (ignoring gas leakage in the pipeline, the sum of the volumetric flow rate changes δV at each end is the volumetric flow rate δV of the compressed air flowing out of the closed container). This equivalent model can eliminate the analytical interference caused by the complex topology of the network (such as multiple branches, variable pipe diameter, long-distance transportation), and transform the nonlinear network flow problem into an intuitive "container filling and venting" physical model. This significantly reduces the difficulty of mathematical modeling and computational complexity. It can quickly deduce the correlation between network pressure, flow rate and load changes, and ensure the accuracy of core parameter calculations (such as pressure change trends and flow supply and demand balance). This lays a simple and reliable analytical foundation for subsequent load sensing and flow prediction, which meets the needs of nuclear facility compressed air systems for rapid response to changes in operating conditions.

[0084] 2. Detect the real-time pressure and flow rate at each end of the pipeline network, perceive changes in the gas load at the end based on the real-time pressure and flow rate, and predict the total compressed air demand flow rate of the pipeline network; This "real-time monitoring + demand forecasting" mode avoids the prediction lag problem caused by the traditional experience-based flow rate estimation, and can detect load fluctuations in advance (such as users 3, 4, and 5 using gas intermittently at the same time), reserve reaction time for the adjustment of air compressor operation strategy, prevent large fluctuations in pipeline network pressure caused by flow supply and demand imbalance, and ensure stable gas supply for safety-level equipment and process equipment.

[0085] 3. Based on the predicted total demand flow, combined with flow matching strategies, the individual parameters of each air compressor, and preset operating rules, the air compressor operating strategies are adjusted to maintain relatively stable compressed air system network pressure, resulting in optimized air compressor unit operating status. For example, for centrifugal air compressors, continuous flow regulation is achieved by adjusting the guide vanes (IGV) and vent valves (BOV), precisely matching real-time flow demand; for screw air compressors, reasonable loading and unloading pressure bands are set to reduce start-up and shutdown frequency, minimizing energy waste and mechanical wear caused by frequent equipment starts and stops. This differentiated adjustment method avoids overpressure in the network caused by "oversupply" of air compressors or insufficient pressure caused by "undersupply," maintaining relatively stable network pressure, while also reducing unnecessary energy expenditure. This aligns with the design requirements of "stable, reliable, energy-saving, and environmentally friendly" compressed air systems in nuclear facilities, significantly improving unit operating efficiency and economy.

[0086] like Figure 7 As shown, by detecting the real-time pressure and flow rate of each terminal, the system predicts the total flow rate based on this information, and then makes a decision on the number of terminals required. Next, a standby terminal is selected and a standby command is issued, followed by a check to see if the action conditions are met. If not, the process ends; if so, the process is further subdivided:

[0087] 1. If the conditions for additional investment are met, first determine the required air compressor capacity of the system, and then select the air compressor that meets the capacity requirements and has the shortest operating time.

[0088] 2. If the conditions for reducing the number of air compressors are met, first determine the remaining air compressor capacity of the system, and then select the air compressor that meets the capacity requirements and has the longest operating time.

[0089] 3. If the replacement conditions are met, determine the number of the air compressor that needs to be replaced.

[0090] 4. Integrate the results of increasing, decreasing, or replacing units to output the unit number decision. The entire process aims to scientifically decide the number of air compressors to operate by monitoring and analyzing various aspects such as unit parameters, terminal parameters, and equipment status, so as to ensure efficient and stable air supply from the compressed air system.

[0091] Step S103: Real-time acquisition of pipeline operation parameters of the compressed air pipeline system and feedback to adjust the control strategy.

[0092] Specifically, multi-dimensional operating parameters can be collected from sensors, control cabinets, and equipment distributed throughout the compressed air pipeline network via a communication module (using the Modbus-TCP protocol). These parameters include:

[0093] Pipeline network core parameters: Real-time pressure (unit: barA) is collected at each node (such as the air compressor station outlet, the inlet of user branch pipes 3 / 4 / 5 / 6, and the end of the pipeline) using pressure sensors; real-time flow (unit: N) is collected from the main pipe and each branch pipe using flow sensors. The real-time temperature of compressed air in the pipeline network (unit: K) is collected by a temperature sensor.

[0094] Equipment operating parameters: The start / stop status, outlet pressure, operating current, and cumulative operating time of each air compressor are collected from the air compressor control cabinet, and the real-time opening degree (unit: %) of key valves (such as pressure reducing valves and venting valves) is collected from the valve controller.

[0095] Load change parameters: Real-time monitoring of gas load changes at the user end (such as air lifters and compressed air injection pumps) using mass flow sensors or volume flow sensors, recording the start time, load increment, and duration of intermittent load surges.

[0096] All collected parameters are transmitted via fiber optic network to the compressed air system operation status database at the software platform layer, and are updated and stored at a frequency of 1 second per update, forming a real-time parameter ledger and historical data curves to support subsequent queries and analysis.

[0097] The predictive intelligent control and gas supply distribution module calls up parameter data from the database in real time and compares it with preset control thresholds (set based on numerical simulation results). The control strategy is adjusted based on the deviation. A specific scenario example is as follows:

[0098] Pressure fluctuation adjustment scenario: When a sudden drop in the pressure of user's 5th branch pipe is detected (e.g., from 9.5 barA to 9.2 barA, with a deviation exceeding the preset threshold of 0.1 bar), and the pressure deviation change rate reaches -0.02 bar / s, the predictive intelligent control and gas supply distribution module determines that the pressure fluctuation is caused by a sudden increase in intermittent load and immediately triggers two adjustments:

[0099] Send a command to the intelligent gas supply distribution module to increase the opening of the pressure reducing valve of the user's 5th branch pipe through fuzzy self-tuning PID control, and stabilize the pressure after the valve within the range of 9.4±0.01 bar;

[0100] Based on traffic matching strategies, predict the total demand traffic increment (e.g., from 200...). Increased to 265 The system sends a command to the air compressor unit to start one standby screw air compressor (originally two, now three), and increases the total air supply to 270 by adjusting the guide vanes (IGV). To ensure a balance between supply and demand.

[0101] Critical operating condition early warning scenario: When users 3, 4, and 5 simultaneously experience intermittent load surges (load increments of 30, 25, and 65 respectively). When the pressure at the compressor station outlet drops to 9.4 barA (close to the critical pressure threshold of 9.38 barA), the system immediately triggers an early warning:

[0102] The operation status monitoring interface will display a pop-up message indicating "multi-user collaborative load critical state" and simultaneously push the warning information to the operation and maintenance terminal.

[0103] The system automatically adjusts the air compressor start-up and shutdown strategy, reducing the centrifugal air compressor start-up time from 15 seconds to 10 seconds, and starts the fourth air compressor ahead of schedule. The pressure regulator's air supply valve slows down the rate of pressure drop, preventing the pressure from falling below the critical value.

[0104] Long-term optimization and adjustment scenario: Through analysis of historical data stored in the database (such as the pressure drop curve of user 6 branch pipe within 1 month), it was found that due to the long distance and small pipe diameter, the pressure drop of user 6 was consistently maintained at 0.15~0.16 bar under continuous operating conditions (exceeding the design threshold of 0.15 bar). Based on the prediction, the intelligent control and gas supply distribution module, combined with the pipeline network optimization design program, generated parameter adjustment suggestions: increase the pipe diameter of user 6 branch pipe from DN50 to DN65. After simulation verification, the suggestions were pushed to the operation and maintenance personnel. After the modification was implemented, the pressure drop of user 6 branch pipe stabilized at 0.13~0.14 bar, meeting the design requirements.

[0105] This invention, through high-frequency parameter acquisition and real-time feedback at 1 second per instance, can quickly capture dynamic changes such as intermittent load surges and equipment anomalies. Compared to traditional manual inspections (response cycles exceeding 30 minutes), it reduces the control strategy adjustment lag time to the second level. For example, in a scenario of a user's 3+4+5 coordinated load surge, pre-starting the backup air compressor and pressure stabilizing tank can prevent the pressure from falling below the critical value of 9.38 barA, preventing the emergency air compressor from entering a dormant state due to accidental start-up or shutdown, and ensuring safe gas supply capacity under nuclear facility accident conditions. Relying on the linkage between real-time parameter feedback and fuzzy self-tuning PID control, the pressure fluctuation at the end of the pipeline network can be strictly controlled within the range of 0.01~0.05 bar, meeting the stringent pressure stability requirements of safety-grade instrumentation and process equipment (such as air lifters). At the same time, the unit adjustment strategy based on flow matching can avoid "oversupply" or "undersupply" of air compressors, reduce mechanical wear caused by frequent equipment start-ups and shutdowns (e.g., reducing the number of screw air compressor loading and unloading times by 30%), extend equipment life, and reduce operation and maintenance costs. Real-time collection of historical parameters provides data support for pipeline network optimization. By analyzing load change patterns (such as user 5's intermittent load being concentrated between 9:00 and 11:00 every day), the air compressor operation plan can be optimized (such as starting one standby machine in advance during this period and reducing the number of machines in operation during off-peak periods), thereby reducing ineffective energy consumption.

[0106] This invention calculates the flow characteristics of compressed air pipelines by establishing nodal mass-energy conservation equations and component momentum conservation equations. The variables to be solved include the flow rate at each port of the component, the nodal temperature, and the pressure.

[0107] A system of nonlinear equations is constructed, with the number of equations matching the number of variables to be solved. The Newton-Raphson method is used to iteratively solve the system to obtain the parameters at each location in the pipeline network, providing data support for numerical simulation and control strategy formulation.

[0108] The embodiments of the present invention can quantify and capture the coupling relationship of "pressure-flow-temperature" in the pipeline network by using the equations of conservation of mass energy at nodes and conservation of momentum of components, thus avoiding the calculation deviations caused by neglecting the interaction of components and energy loss at nodes in traditional empirical formulas. For example, the steady-state / transient analysis of the Flomaster simulation model (such as the pressure drop of 0.10665 bar in the main pipe caused by a sudden load increase in user 5 and a pressure drop of 0.15255 bar in continuous operation for user 6) all use the flow characteristic data calculated by this method as input, ensuring that the simulation results are consistent with the actual pipeline network operation, and providing data support for the formulation of predictive control strategies (such as the number of air compressors to start and stop, and the selection of pressure stabilizing tanks). This method can be adapted to various operating conditions of nuclear facility compressed air systems, such as steady-state (such as continuous production conditions) and transient (such as intermittent load increases and air compressor switching). Under steady-state conditions, it can calculate the uniformity of pipeline pressure distribution (such as whether the pressure drop deviation of user 1-6 branches is ≤0.2 bar), and under transient conditions, it can capture the pressure drop rate (such as -0.048 bar / s when the load increases by 2.0 times). For example, when users 3, 4, and 5 are simultaneously under intermittent load, the minimum outlet pressure of the air compressor station, 9.38 barA, can be calculated using this method. This provides a precise basis for setting pressure warning thresholds and starting standby air compressors in advance, thus preventing the pressure from falling below the allowable range of the safety-level equipment.

[0109] This embodiment also provides an intelligent control and gas distribution system for a nuclear facility compressed air system network. This system is used to implement the above embodiments and preferred embodiments, and details already described will not be repeated. As used below, the term "module" can refer to a combination of software and / or hardware that performs a predetermined function. Although the systems described in the following embodiments are preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0110] This embodiment provides an intelligent control and gas distribution system for the compressed air system network of a nuclear facility, such as... Figure 8 As shown, it includes the application layer and the platform layer, including:

[0111] The application layer includes: a compressed air system operation status monitoring interface module 801, which is used to dynamically display the operating parameters of the main equipment of the compressed air system. The operating parameters include at least the pressure parameters and flow parameters in the compressed air system pipeline network, so as to present the operating status of the compressed air system in real time.

[0112] The compressed air system pipeline modeling interface module 802 includes three sub-modules: a component library, a canvas, and an output interface. The component library pre-stores the main component types required for the compressed air system pipeline, including at least straight pipes, bends, tees, and valves. The canvas serves as a configurable operation area for building the pipeline model, allowing users to construct a graphical model of the compressed air system pipeline by dragging and dropping components and connecting component ports. The output interface converts the graphical compressed air system pipeline model into an input card file that can be recognized by the compressed air system pipeline flow characteristic calculation program.

[0113] The compressed air system pipeline modeling interface module of this invention utilizes three sub-modules—a component library, a canvas, and an output interface—to work collaboratively. The component library pre-stores core components such as straight pipes, meeting the basic requirements for pipeline modeling. The canvas supports configurable drag-and-drop connections, reducing the difficulty of user modeling operations and improving model building efficiency and intuitiveness. The output interface automatically converts the graphical model into a calculation program input card file, avoiding manual conversion errors and ensuring smooth integration between the model and the calculation process. The compressed air system operation status monitoring interface module dynamically displays key parameters such as pressure and flow rate, helping users to monitor the system's operating status in real time, promptly detect parameter anomalies, and provide intuitive basis for operation and maintenance decisions.

[0114] The platform layer includes: Numerical simulation module 803, which is used to build a simulation model of the compressed air pipeline system and to perform numerical simulations of the flow and pressure characteristics of the compressed air pipeline under different air compressor station distribution settings, operating conditions, and intermittent loads of different process equipment.

[0115] The intelligent control and air supply distribution module 804 is used to take control measures for various operating conditions in the compressed air system based on data generated by numerical simulation and based on predictive control strategies. These measures include: adjusting the pressure at the end of the compressed air pipeline network using an intelligent fuzzy self-tuning PID control method, and optimizing the operating status of the air compressor units in the compressed air pipeline network based on a flow matching strategy.

[0116] The communication module 805 allows users to collect real-time pipeline operation parameters of the compressed air pipeline system and provide feedback to adjust control strategies.

[0117] The compressed air pipeline flow characteristic calculation module 806 is used to calculate the flow characteristics of the compressed air pipeline by establishing the mass-energy conservation equations of the nodes and the momentum conservation equations of the components. The variables to be solved include the flow rate at each port of the component, the temperature and pressure of the nodes. A set of nonlinear equations is constructed, with the number of equations being consistent with the number of variables to be solved. The Newton-Raphson method is used to iteratively solve the equations to obtain the parameters at each location of the pipeline, providing data support for numerical simulation and control strategy formulation.

[0118] The compressed air system operation status database module 807 stores pipeline flow and pressure characteristic data calculated using simulation and optimization methods, as well as pipeline operation data collected through acquisition interfaces. This module integrates and stores simulated pipeline flow and pressure characteristic data with real-time operation data acquired through acquisition interfaces, forming a unified data ledger. On one hand, it provides historical data support for numerical simulation and optimization analysis, allowing for the tracking of pipeline parameter changes under different operating conditions and facilitating iterative optimization of control strategies. On the other hand, comparing real-time data with simulated data verifies model accuracy and promptly detects data anomalies (such as indicating sensor malfunctions when the collected data deviates significantly from the simulated data). Simultaneously, centralized data storage facilitates subsequent querying, statistics, and analysis, providing a basis for maintenance personnel to assess long-term system operation trends and formulate maintenance plans, avoiding management chaos and information loss caused by data dispersion.

[0119] The equipment control module 808 converts control commands from various devices into control currents. This module transforms abstract equipment control commands into specific control currents, achieving precise matching between control commands and equipment actuators. Compared to manual control signal conversion, it avoids human error and ensures stable operation of equipment such as air compressors and valves according to preset commands, such as precisely adjusting air compressor start / stop and valve opening to guarantee stable pipeline pressure and flow. Furthermore, the standardized command conversion process adapts to different models and types of equipment, improving module versatility and reducing the difficulty of control adaptation due to equipment differences, providing crucial execution guarantees for the automated and intelligent control of compressed air systems.

[0120] Further functional descriptions of the above modules and units are the same as those in the corresponding embodiments described above, and will not be repeated here.

[0121] In this embodiment, the intelligent control and gas distribution system of the nuclear facility compressed air system network is presented in the form of functional units. Here, a unit refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and memory that execute one or more software or fixed programs, and / or other devices that can provide the above functions.

[0122] This invention also provides a computer device having the above-described features. Figure 8 The diagram shows an intelligent control and gas distribution system for the compressed air system network of a nuclear facility.

[0123] Please see Figure 9 , Figure 9 This is a schematic diagram of the structure of a computer device provided in an optional embodiment of the present invention, such as... Figure 9As shown, the computer device includes one or more processors 10, memory 20, and interfaces for connecting the components, including high-speed interfaces and low-speed interfaces. The components communicate with each other via different buses and can be mounted on a common motherboard or otherwise installed as needed. The processors can process instructions executed within the computer device, including instructions stored in or on memory to display graphical information of a GUI on external input / output devices (such as display devices coupled to the interfaces). In some alternative implementations, multiple processors and / or multiple buses can be used with multiple memories and multiple memory modules, if desired. Similarly, multiple computer devices can be connected, each providing some of the necessary operations (e.g., as a server array, a group of blade servers, or a multiprocessor system). Figure 9 Take a processor 10 as an example.

[0124] Processor 10 may be a central processing unit, a network processor, or a combination thereof. Processor 10 may further include a hardware chip. The hardware chip may be an application-specific integrated circuit (ASIC), a programmable logic device (PLD), or a combination thereof. The programmable logic device may be a complex programmable logic device (CAMP), a field-programmable gate array (FPGA), a general-purpose array logic (GDA), or any combination thereof.

[0125] The memory 20 stores instructions executable by at least one processor 10 to cause at least one processor 10 to perform the method shown in the above embodiments.

[0126] The memory 20 may include a program storage area and a data storage area. The program storage area may store the operating system and applications required for at least one function; the data storage area may store data created based on the use of the computer device. Furthermore, the memory 20 may include high-speed random access memory and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some alternative embodiments, the memory 20 may optionally include memory remotely located relative to the processor 10, and these remote memories may be connected to the computer device via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

[0127] The memory 20 may include volatile memory, such as random access memory; the memory may also include non-volatile memory, such as flash memory, hard disk or solid-state drive; the memory 20 may also include a combination of the above types of memory.

[0128] The computer device also includes a communication interface 30 for communicating with other devices or communication networks.

[0129] This invention also provides a computer-readable storage medium. The methods described above according to embodiments of the invention can be implemented in hardware or firmware, or implemented as computer code that can be recorded on a storage medium, or implemented as computer code downloaded via a network and originally stored on a remote storage medium or a non-transitory machine-readable storage medium and then stored on a local storage medium. Thus, the methods described herein can be processed by software stored on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. The storage medium can be a magnetic disk, optical disk, read-only memory, random access memory, flash memory, hard disk, or solid-state drive, etc.; further, the storage medium can also include combinations of the above types of memory. It is understood that computers, processors, microprocessor controllers, or programmable hardware include storage components capable of storing or receiving software or computer code, which, when accessed and executed by the computer, processor, or hardware, implements the methods shown in the above embodiments.

[0130] A portion of this invention can be applied as a computer program product, such as computer program instructions, which, when executed by a computer, can invoke or provide the methods and / or technical solutions according to the invention through the operation of the computer. Those skilled in the art will understand that the forms in which computer program instructions exist in a computer-readable medium include, but are not limited to, source files, executable files, installation package files, etc. Correspondingly, the ways in which computer program instructions are executed by a computer include, but are not limited to: the computer directly executing the instructions, or the computer compiling the instructions and then executing the corresponding compiled program, or the computer reading and executing the instructions, or the computer reading and installing the instructions and then executing the corresponding installed program. Here, the computer-readable medium can be any available computer-readable storage medium or communication medium accessible to a computer.

[0131] Although embodiments of the invention have been described in conjunction with the accompanying drawings, those skilled in the art can make various modifications and variations without departing from the spirit and scope of the invention, and such modifications and variations all fall within the scope defined by the appended claims.

Claims

1. An intelligent control and air supply distribution method for a nuclear facility air compression system pipe network, characterized in that, The method comprises the following steps: constructing a simulation model of the compressed air pipe network system, performing numerical simulation on the flow and pressure characteristics of the compressed air pipe network under different air compression station distribution settings, operating conditions, and intermittent loads of different process equipment, the numerical simulation comprising steady-state simulation, transient simulation, and configuration optimization analysis; the steady-state simulation is used to simulate the branch pipe pressure drop, total pipe pressure drop variation, and flow influence law when the intermittent loads of different users suddenly increase, and to determine the coupling effect of user location and load increment on system pressure; the transient simulation is used to simulate the system pressure dynamic response characteristics when the intermittent loads suddenly increase, including the pressure drop rate, the influence of air compressor start-up time and number on pressure recovery time, and the critical pressure value under multi-user coordinated load; the configuration optimization analysis is performed around the air compression station distribution, pipe network scale, surge tank volume, and air compressor start-up and stop strategy, and is used to determine the optimal configuration parameters; based on the data generated by the numerical simulation, a control strategy is used to take control measures for various operating conditions in the compressed air system, including: using an intelligent fuzzy self-tuning PID control method to adjust the end-of-pipe pressure of the compressed air pipe network system, and using a flow matching strategy to optimize the operating state of the air compressor unit of the compressed air pipe network system; the intelligent fuzzy self-tuning PID control method comprises: taking the pressure deviation and rate of change of the end-of-pipe pressure of the compressed air pipe network system as the input of the fuzzy controller, and taking the proportional coefficient correction value, integral coefficient correction value, and differential coefficient correction value of the PID controller as the output, so as to establish an online tuning relationship between the input and output through fuzzy mathematical reasoning, and control the end-of-pipe pressure fluctuation within a preset range; the flow matching strategy comprises: equivalent the compressed air supply pipe network of the compressed air system to a closed container with an effective volume, equivalent the air supply of the air compressor to the charging of the closed container, and equivalent the use of the production equipment at the end of the pipe network to the discharge from the closed container; detecting the real-time pressure and real-time flow of each end of the pipe network, sensing the load change of the end of the pipe network based on the real-time pressure and real-time flow, and predicting the total compressed air demand flow of the pipe network; based on the predicted total demand flow, combining the flow matching strategy, the parameters of each air compressor, and the preset operating rules, adjusting the operating strategy of the air compressor to keep the pressure of the compressed air system pipe network relatively stable, and obtaining the optimized operating state of the air compressor unit; real-time acquisition of the pipe network operating parameters of the compressed air pipe network system and feedback adjustment of the control strategy.

2. The method of claim 1, wherein, When constructing the simulation model of the compressed air pipe network system, a one-dimensional thermal fluid simulation software is used, and the modeling content comprises element selection, topology structure building, and boundary condition setting, wherein the elements include straight pipes, elbow pipes, tee pipes, valves, air compression stations, and user ends; after modeling, model debugging and verification are performed to ensure that the model error is within a preset range, wherein the model debugging and verification comprise: design variable definition: taking the pipe diameter, valve opening, and resistance parameter in the pipe network as adjustable design variables, wherein the design variables include continuous variables, discrete variables, or a combination thereof; Constraint setting: Establish constraints including pressure fluctuation range, flow supply capacity and pipe network structure limitations to ensure that the optimization results are within the engineering feasible range; Objective function construction: Take the expected flow matching degree of each branch in the pipe network as the main optimization target, while considering the minimum energy consumption and gas supply stability indicators; Iterative optimization: Use an analysis-driven optimization framework to perform pipe network flow characteristic analysis based on the current design variable values at each iteration, obtain pressure distribution and flow distribution data, evaluate the degree of satisfaction of the objective function through the optimization algorithm and generate a new combination of design variables, repeat the above process until the convergence condition is met or the maximum number of iterations is reached, and obtain the optimal pipe network configuration scheme.

3. The method according to any of claims 1 or 2, characterized in that, Also includes: Calculate the flow characteristics of the compressed air pipe network by establishing node energy conservation equations and element momentum conservation equations. The variables to be solved include the flow at each port of the element, the temperature and pressure of the node. Construct a nonlinear equation system with the same number of equations as the number of variables to be solved, and use the Newton-Raphson method to iteratively solve for the parameters at each location in the pipe network to provide data support for numerical simulation and control strategy development.

4. An intelligent control and gas distribution system for a nuclear facility air compression system piping network, characterized by, The system includes: A numerical simulation module for building a compressed air pipe network system simulation model, simulating the flow and pressure characteristics of the compressed air pipe network under different air compression station distribution settings, operating conditions, and different process equipment intermittent loads. The numerical simulation includes steady-state simulation, transient simulation, and configuration optimization analysis. The steady-state simulation is used to simulate the branch pressure drop, total pipe pressure drop changes, and flow influence law when different users have intermittent load surges, and to determine the coupling effect of user location and load increment on system pressure. The transient simulation is used to simulate the system pressure dynamic response characteristics when the intermittent load surges, including the pressure drop rate, air compressor startup time and number of influences on pressure recovery time, and critical pressure value under multi-user coordinated load. Configuration optimization analysis focuses on air compression station distribution, pipe network size, surge tank volume, and air compressor start-stop strategy to determine the optimal configuration parameters. An intelligent control and gas distribution module for generating data based on numerical simulation, and adopting control strategies to deal with various conditions in the compressed air system, including using intelligent fuzzy self-tuning PID control method to adjust the end pressure of the compressed air pipe network system, and optimizing the operation state of the air compressor unit based on the flow matching strategy. The intelligent fuzzy self-tuning PID control method adjusts the end pressure of the compressed air pipe network system by using the pressure deviation and rate of change of the pressure deviation as the input of the fuzzy controller, and the proportional coefficient correction value, integral coefficient correction value and differential coefficient correction value of the PID controller as the output. Through online tuning of the input-output relationship established by fuzzy mathematics reasoning, the pipe network end pressure fluctuation is controlled within the preset range. The air compression pipe network system operation state is optimized based on the flow matching strategy, including: the compressed air system supply pipe network is equivalent to a closed container with an effective volume, the air compressor supply to the pipe network is equivalent to isothermal charging to the closed container, and the pipe network end production device is equivalent to isothermal discharge from the closed container; the real-time pressure and real-time flow of each end of the pipe network are detected, the end gas load change is perceived based on the real-time pressure and real-time flow, and the total compressed air demand flow of the pipe network is predicted; based on the total demand flow obtained by prediction, the flow matching strategy, the self parameters of each air compressor and the preset operation rules are combined, the air compressor operation strategy is adjusted to keep the pipe network pressure of the compressed air system relatively stable, and the optimized air compressor unit operation state is obtained; The communication module is used for real-time collection of pipe network operation parameters of the compressed air pipe network system and feedback of adjustment control strategy.

5. The system of claim 4, wherein, Further comprising: The compressed air system pipe network modeling interface module includes three sub-modules of an element library, a canvas and an output interface; the element library pre-stores main element types required by the compressed air system pipe network, at least including straight pipes, elbow pipes, three-way pipes and valves; the canvas is used as a configuration type operation area for pipe network model building, supports the user to build a graphical model of the compressed air system pipe network by dragging elements and connecting element ports, and the output interface is used for converting the graphical compressed air system pipe network model into an input card file recognizable by a compressed air system pipe network flow characteristic calculation program; the compressed air system operation state monitoring interface module is used for dynamic display of operation parameters of main equipment of the compressed air system, and the operation parameters at least include pressure parameters and flow parameters in the compressed air system pipe network, so as to present the compressed air system operation state in real time; The compressed air pipe network flow characteristic calculation module is used for calculating the compressed air pipe network flow characteristics by establishing node energy conservation equations and element momentum conservation equations, the to-be-solved variables including element port flow, node temperature and pressure; a nonlinear equation set is constructed, the number of equations is consistent with the number of to-be-solved variables, and the Newton-Raphson method is used for iterative solution to obtain parameters of each position of the pipe network, providing data support for numerical simulation and control strategy formulation; The compressed air system operation state database module is used for storing pipe network flow and pressure characteristic data calculated by the simulation method and the optimization method and pipe network operation data collected by the collection interface; and the device control module is used for converting control instructions of each device into control currents.

6. A computer device, comprising: Comprising: A memory and a processor, which are communicatively connected, the memory stores computer instructions, and the processor executes the computer instructions to perform the nuclear facility compressed air system pipe network intelligent control and gas supply distribution method in any one of claims 1 to 3.

7. A computer readable storage medium characterized by The computer readable storage medium stores computer instructions, and the computer instructions are used to make the computer execute the nuclear facility compressed air system pipe network intelligent control and gas supply distribution method in any one of claims 1 to 3.

Images