WO2023245403A1

WO2023245403A1 - Optimization method and apparatus for fluid network system

Info

Publication number: WO2023245403A1
Application number: PCT/CN2022/100041
Authority: WO
Inventors: 江宁; 王德慧
Original assignee: 西门子股份公司; 西门子（中国）有限公司
Priority date: 2022-06-21
Filing date: 2022-06-21
Publication date: 2023-12-28

Abstract

Provided in the present invention is an optimization method for a fluid network system. The optimization method comprises: acquiring a pipeline flow chart of a fluid network system; establishing simulation models of devices and a main pipe in the fluid network system, wherein the simulation models of the devices and the main pipe comprise a mechanism model and a data model; establishing a system simulation model of the fluid network system according to the simulation models of the devices and the main pipe and the pipeline flow chart; and establishing a system parameter optimization model according to an objective function and the system simulation model, solving optimal key parameters of the system parameter optimization model by using a least square method, and operating the fluid network system according to the optimal key parameters.

Description

Optimization method and device of fluid network system

Technical field

The present invention mainly relates to the field of energy management, and in particular, to an optimization method and device for a fluid network system.

Background technique

Fluid network is a simple abstraction of a continuous production process and is widely used in power generation, chemical industry, water treatment and other industries. In a fluid network, changes in a few key parameters will affect comprehensive changes in the state of the entire fluid network system, which will have a significant impact on the energy consumption and environmental performance of the fluid network system. Therefore, the optimization of a few key parameters will have a significant impact on improving the entire fluid network. The economic performance and environmental performance of the system are crucial.

In the existing technology, each device in the fluid network is modeled separately, and methods such as transfer functions and differential equations are used to represent the input and output characteristics of the device. A model of the entire fluid network is built on the basis of a single device, and then mixed integer linear optimization is used. The model is solved. The problem with this method is that the mixed integer linear optimization model is very difficult to express nonlinear models, and most of the performance models of actual equipment are nonlinear models. If methods such as local linearization are used to convert the nonlinear model into a model that can be processed by the mixed integer linear optimization algorithm, the amount of calculation will increase exponentially, convergence will not be possible within the specified time, and a balance between calculation accuracy and calculation speed will not be achieved. The problem.

Contents of the invention

In order to solve the above technical problems, the present invention provides an optimization method and device for a fluid network system to improve the optimization speed of the fluid network system.

In order to achieve the above purpose, the present invention proposes an optimization method for a fluid network system. The optimization method includes: obtaining the pipeline flow diagram of the fluid network system; establishing a simulation model of each equipment and mother pipe in the fluid network system. , the simulation model of each equipment and main pipe includes a mechanism model and a data model; establish a system simulation model of the fluid network system according to the simulation model of each equipment and main pipe and the pipeline flow diagram; according to the objective function and The system simulation model establishes a system parameter optimization model, uses the least square method to solve the optimal key parameters of the system parameter optimization model, and runs the fluid network system according to the optimal key parameters. To this end, embodiments of the present invention provide an optimization method for a fluid network system, establish a simulation model of the fluid network system, and use the least squares method to optimize the simulation model. It can handle complex functions, has a wider scope of application, and improves efficiency. Optimize efficiency.

Optionally, establishing a system simulation model of the fluid network system based on the simulation model of each device and main pipe and the pipeline flow diagram includes: establishing a graphical model of the pipeline flow diagram, and converting the graphical The model is converted into structured data, the topological structure of the graphical model is identified according to the structured data, and the system simulation model of the fluid network system is established using the simulation model of each device and the main pipe and the topological structure. To this end, the graphical model can intuitively and abstractly represent the connection relationship between equipment and pipelines, and then the graphical model is converted into XML and JSON formats, which is a topological structure that can be recognized by the machine.

Optionally, establishing a system simulation model of the fluid network system based on the simulation model of each device and main pipe and the pipeline flow diagram includes: receiving a specified value of a variable input by the user, simulating the system The variables in the model are replaced with the specified values. For this reason, by users inputting specified values of variables, the number of variables can be reduced and the complexity of the simulation model can be reduced, thus improving the efficiency of optimization.

Optionally, establishing a system simulation model of the fluid network system based on the simulation model of each device and main pipe and the pipeline flow diagram includes: determining a proportional relationship between two variables, and converting the two variables according to the proportional relationship. The two variables mentioned above are combined into one variable. To this end, through the proportional relationship between user input variables, the number of equation groups can be reduced and the complexity of the simulation model can be reduced, thereby improving the efficiency of optimization.

Optionally, the objective function is system operating cost, which includes fuel cost and operation and maintenance cost, and the optimal key parameters include main pipe temperature, main pipe pressure, equipment power and equipment flow rate. To this end, system operating costs can be controlled to a minimum to improve system economy.

The invention also proposes an optimization device for a fluid network system. The optimization device includes: an acquisition module to acquire the pipeline flow diagram of the fluid network system; and a modeling module to establish each equipment and mother pipe in the fluid network system. The simulation model, the simulation model of each equipment and the main pipe includes a mechanism model and a data model; the simulation module establishes the system simulation of the fluid network system according to the simulation model of each equipment and the main pipe and the pipeline flow chart. Model; optimization module, establishes a system parameter optimization model according to the objective function and the system simulation model, uses the least squares method to solve the optimal key parameters of the system parameter optimization model, and runs the fluid network according to the optimal key parameters system.

Optionally, the simulation module establishes a system simulation model of the fluid network system based on the simulation model of each device and main pipe and the pipeline flow diagram, including: establishing a graphical model of the pipeline flow diagram, and converting The graphical model is converted into structured data, the topology structure of the graphical model is identified according to the structured data, and the simulation model of each device and the main pipe and the topology structure are used to establish the fluid network system. System simulation model.

Optionally, the simulation module establishing a system simulation model of the fluid network system based on the simulation model of each device and main pipe and the pipeline flow diagram includes: receiving a specified value of a variable input by the user, and converting the The variables in the system simulation model are replaced with the specified values.

Optionally, the simulation module establishing a system simulation model of the fluid network system based on the simulation model of each device and main pipe and the pipeline flow diagram includes: determining the proportional relationship between two variables, according to the A proportional relationship combines the two variables into one variable.

Optionally, the objective function is system operating cost, which includes fuel cost and operation and maintenance cost, and the optimal key parameters include main pipe temperature, main pipe pressure, equipment power and equipment flow rate.

The present invention also proposes an electronic device, including a processor, a memory and instructions stored in the memory, wherein when the instructions are executed by the processor, the above method is implemented.

The present invention also proposes a computer-readable storage medium on which computer instructions are stored, which execute the method as described above when executed.

Description of the drawings

The following drawings are only intended to schematically illustrate and explain the present invention and do not limit the scope of the present invention. in,

Figure 1 is a flow chart of an optimization method for a fluid network system according to an embodiment of the present invention;

Figure 2 is a schematic diagram of an optimization device of a fluid network system according to an embodiment of the present invention;

Figure 3 is a schematic diagram of an electronic device according to an embodiment of the present invention.

Explanation of reference signs

Optimization method of 100 fluid network system

Steps 110-140

Optimization device of 200 fluid network system

210 Get module

220 Modeling Module

230 simulation module

240 optimization module

300 Electronic Equipment

310 processor

320 memory

Detailed ways

In order to have a clearer understanding of the technical features, purposes and effects of the present invention, the specific embodiments of the present invention will now be described with reference to the accompanying drawings.

Many specific details are set forth in the following description to fully understand the present invention, but the present invention can also be implemented in other ways different from those described here, so the present invention is not limited to the specific embodiments disclosed below.

As shown in this application and claims, words such as "a", "an", "an" and/or "the" do not specifically refer to the singular and may include the plural unless the context clearly indicates an exception. Generally speaking, the terms "comprising" and "comprising" only imply the inclusion of clearly identified steps and elements, and these steps and elements do not constitute an exclusive list. The method or apparatus may also include other steps or elements.

The present invention provides an optimization method for a fluid network system. Figure 1 is a flow chart of an optimization method 100 for a fluid network system according to an embodiment of the present invention. As shown in Figure 1, the optimization method 100 includes:

Step 110: Obtain the pipeline flow diagram of the fluid network system.

The fluid network system can be abstracted into two objects: equipment and main pipe. The equipment has input and output of the medium, or one of them. The physical properties of the input and output medium, such as temperature, pressure, flow rate, etc., may change; the parent pipe represents the interconnected pipelines that can ignore geographical differences and transmission losses. In the same mother pipe, the state quantities such as temperature and pressure of the medium are the same. If the temperature and pressure at both ends of a pipeline are different due to factors such as pipe length, pipe diameter, etc., then this pipeline is treated as a piece of equipment in the embodiment of the present invention. The pipeline flow diagram represents the connection relationship between the equipment and main pipes in the fluid network system. The pipeline flow diagram can be a PFD diagram (process flow diagram) or a PID diagram (process instrumentation drawing). The PFD diagram or PID diagram can be drawn from the fluid network system. Get it on site.

Step 120: Establish a simulation model of each device and main pipe in the fluid network system. The simulation model of each device and main pipe includes a mechanism model and a data model.

Historical big data can be used to establish simulation models of each equipment and main pipe in the fluid network system. The simulation models of each equipment and main pipe include mechanism models and data models. In the embodiment of the present invention, the mechanism model refers to a system model established based on the mechanism of the fluid network system. The mechanism can be a physical or chemical change law. The data model is an abstraction of real-world data characteristics, including data structure and data operations. and data constraints. The dominant factors and characteristic curves can be obtained through the mechanism model and data model, and these dominant factors and characteristic curves will be used for system simulation modeling in subsequent steps.

Step 130: Establish a system simulation model of the fluid network system based on the simulation models of each equipment and main pipe and the pipeline flow diagram.

For a fluid network system, it can be abstracted as a model in which fluid flows into the system through equipment, undergoes property conversion through a series of equipment, and then flows out of the system. The equipment is connected to each other through mother pipes. For the mother pipe, its key state parameters include temperature T and pressure P, and for the equipment, its key state parameters include power w and flow rate G. Its main control equations include,

For the mother pipe:

∑G _in +∑G _out =0 (1)

For devices:

ΔP＝P _out -P _in ＝f _p (w,G,T,P,X) (2)

ΔT＝T _out -T _in ＝f _T (w,G,T,P,X) (3)

W _in =f _eff (w,G,T,P,X) (4)

Among them, G _in and G _out represent the input flow and output flow of the main pipe, P _out and P _in represent the output pressure and input pressure of the equipment, T _out and T _in represent the output temperature and input temperature of the equipment, and W _in represents the input of the equipment. Power, f _p , f _T , f _eff are the relationship functions between ΔP, ΔT and W _in and other key parameters power w, flow rate G, temperature T and pressure P. X represents other related variables. The input and output P and T of the device depend on the input and output mother tube to which it is connected. f _p , f _T , and f _eff can be obtained from step 120, that is, from the simulation model or the big data model. By combining the above constraint equations (1)-(4) and solving them, the state of the entire fluid network system can be obtained, that is, the system simulation model of the fluid network system.

In some embodiments, establishing a system simulation model of the fluid network system based on the simulation model of each equipment and main pipe and the pipeline flow diagram includes: establishing a graphical model of the pipeline flow diagram, converting the graphical model into structured data, and converting the graphical model into structured data according to the structure. The topology structure of the graphical model is identified using the data, and the simulation model and topology structure of each equipment and main pipe are used to establish a system simulation model of the fluid network system. For example, draw a graphical model of the fluid network based on the PFD (Pipeline Flow Diagram) diagram or PID diagram of the fluid network system. The graphical model can intuitively and abstractly represent the connection relationship between equipment and pipelines, and then convert the graphical model into XML. and JSON format, which is a topological structure that can be recognized by the machine.

In some embodiments, establishing a system simulation model of the fluid network system based on the simulation model of each equipment and main pipe and the pipeline flow diagram may include: receiving a specified value of a variable input by the user, and converting the variable in the system simulation model to the specified value. value substitution. Specifically, in some application scenarios, the values of some variables are specified. By users inputting the specified values of the variables, the number of variables can be reduced and the complexity of the simulation model can be reduced, thereby improving the efficiency of optimization.

In some embodiments, establishing a system simulation model of the fluid network system based on the simulation model of each equipment and main pipe and the pipeline flow diagram may include: determining the proportional relationship between two variables, and merging the two variables into one according to the proportional relationship. variable. Specifically, in some application scenarios, there is a proportional relationship between some variables. By user inputting the proportional relationship between these variables, the number of equation groups can be reduced, the complexity of the simulation model can be reduced, and the optimization results can be improved. efficiency.

Step 140: Establish a system parameter optimization model based on the objective function and the system simulation model, use the least squares method to solve for the optimal key parameters of the system parameter optimization model, and run the fluid network system based on the optimal key parameters.

For the constraint equations (1)-(4), it can be written as F(X)=0, where F(X), this is the system simulation model, and X can be solved using the least squares method. For general optimization problems, the number of X is usually greater than the number of equations, so multiple X can be obtained to satisfy F(X)=0.

Establish a system parameter optimization model based on the objective function and system simulation model, that is, the objective function of the optimization problem is also added as a constraint condition to the constraint equation system, that is, ∑obj _i *x _i = 0, where ∑obj _i *x _i is the objective function, obj _i is the coefficient of the variable in the objective function, i is the number of variables in the system, x _i is the i-th variable, this is the system parameter optimization model. Through the least squares method, a unique set of solutions can be obtained, when F(X ) = 0, so that ∑ obj _i *x _i is minimized. This set of solutions is the optimal key parameters. By running the fluid network system based on this set of optimal key parameters, the optimization goal of minimizing the objective function can be achieved.

In some embodiments, the objective function is the system operating cost, which includes fuel cost and operation and maintenance cost, and the optimal key parameters include main pipe temperature, main pipe pressure, equipment power and equipment flow rate. Specifically, the objective function is the system operating cost. The system operating cost needs to be controlled within the minimum range to improve the economy of the system. The objective function is added as a constraint to the simulation model, and the least squares method is used to solve a set of mother pipe temperatures, Main pipe pressure, equipment power and equipment flow, etc., by adjusting the fluid network system to this set of main pipe temperature, main pipe pressure, equipment power, equipment flow, etc., the optimal operation of the fluid network system can be achieved.

The embodiment of the present invention provides an optimization method for a fluid network system, establishes a simulation model of the fluid network system, uses the least squares method to optimize the simulation model, can handle complex functions, has a wider applicable scope, and improves optimization efficiency.

The present invention also provides an optimization device for a fluid network system. Figure 2 is a schematic diagram of an optimization device 200 for a fluid network system according to an embodiment of the present invention. As shown in Figure 2, the optimization device 200 includes:

The acquisition module 210 acquires the pipeline flow diagram of the fluid network system;

The modeling module 220 establishes a simulation model of each device and mother pipe in the fluid network system. The simulation model of each device and mother pipe includes a mechanism model and a data model;

The simulation module 230 establishes a system simulation model of the fluid network system based on the simulation models of each equipment and main pipe and the pipeline flow diagram;

The optimization module 240 establishes a system parameter optimization model based on the objective function and the system simulation model, uses the least squares method to solve the optimal key parameters of the system parameter optimization model, and runs the fluid network system according to the optimal key parameters.

In some embodiments, the simulation module 230 establishes a system simulation model of the fluid network system based on the simulation models of each equipment and main pipe and the pipeline flow diagram, including: establishing a graphical model of the pipeline flow diagram, and converting the graphical model into structured data. , identify the topology structure of the graphical model based on structured data, and use the simulation model and topology structure of each device and main pipe to establish a system simulation model of the fluid network system.

In some embodiments, the simulation module 230 establishes a system simulation model of the fluid network system based on the simulation model of each equipment and main pipe and the pipeline flow diagram, including: receiving a specified value of a variable input by the user, and converting the variable in the system simulation model to Replace with the specified value.

In some embodiments, the simulation module 230 establishes a system simulation model of the fluid network system based on the simulation model of each equipment and main pipe and the pipeline flow diagram, including: determining the proportional relationship between two variables, and merging the two variables according to the proportional relationship. as a variable.

In some embodiments, the objective function is the system operating cost. The system operating cost includes fuel cost and operation and maintenance cost. The optimal key parameters include main pipe temperature, main pipe pressure, equipment power and equipment flow rate.

The present invention also provides an electronic device 300. FIG. 3 is a schematic diagram of an electronic device 300 according to an embodiment of the present invention. As shown in FIG. 3 , the electronic device 300 includes a processor 310 and a memory 320 . The memory 320 stores instructions, and when the instructions are executed by the processor 310 , the method 100 as described above is implemented.

The present invention also proposes a computer-readable storage medium on which computer instructions are stored, and when executed, the computer instructions execute the method 100 as described above.

Some aspects of the method and device of the present invention may be executed entirely by hardware, may be entirely executed by software (including firmware, resident software, microcode, etc.), or may be executed by a combination of hardware and software. The above hardware or software may be referred to as "data block", "module", "engine", "unit", "component" or "system". The processor may be one or more Application Specific Integrated Circuits (ASIC), Digital Signal Processor (DSP), Digital Signal Processing Device (DAPD), Programmable Logic Device (PLD), Field Programmable Gate Array (FPGA), Processor , controller, microcontroller, microprocessor or combination thereof. Additionally, aspects of the invention may be embodied as a computer product embodied in one or more computer-readable media, the product including computer-readable program code. For example, computer-readable media may include, but are not limited to, magnetic storage devices (e.g., hard disks, floppy disks, tapes, etc.), optical disks (e.g., compact disks (CD), digital versatile disks (DVD), ...), smart cards and flash memory devices (e.g. cards, sticks, key drives...).

A flowchart is used here to illustrate operations performed by methods according to embodiments of the present application. It should be understood that the preceding operations are not necessarily performed in exact order. Instead, the various steps can be processed in reverse order or simultaneously. At the same time, other operations may be added to these processes, or a step or steps may be removed from these processes.

It should be understood that although this specification is described in terms of various embodiments, not each embodiment only contains an independent technical solution. This description of the specification is only for the sake of clarity, and those skilled in the art should take the specification as a whole. , the technical solutions in each embodiment can also be appropriately combined to form other implementations that can be understood by those skilled in the art.

The above descriptions are only illustrative embodiments of the present invention and are not intended to limit the scope of the present invention. Any equivalent changes, modifications and combinations made by those skilled in the art without departing from the concept and principles of the present invention shall fall within the scope of protection of the present invention.

Claims

An optimization method (100) for a fluid network system, characterized in that the optimization method (100) includes:

Obtain the pipeline flow diagram of the fluid network system (110);

Establish a simulation model of each device and main pipe in the fluid network system. The simulation model of each device and main pipe includes a mechanism model and a data model (120);

Establish a system simulation model of the fluid network system (130) according to the simulation model of each equipment and main pipe and the pipeline flow diagram;

Establish a system parameter optimization model according to the objective function and the system simulation model, use the least squares method to solve the optimal key parameters of the system parameter optimization model, and run the fluid network system according to the optimal key parameters (140).
The optimization method (100) according to claim 1, characterized in that establishing the system simulation model (130) of the fluid network system according to the simulation model of each device and the main pipe and the pipeline flow diagram includes: establishing Convert the graphical model of the pipeline flow chart into structured data, identify the topology of the graphical model based on the structured data, and use the simulation models of each equipment and mother pipe and The topology establishes a system simulation model of the fluid network system.
The optimization method (100) according to claim 1 or 2, characterized in that establishing a system simulation model (130) of the fluid network system according to the simulation model of each equipment and main pipe and the pipeline flow diagram includes : Receive a specified value of a variable input by the user, and replace the variable in the system simulation model with the specified value.
The optimization method (100) according to claim 1, characterized in that establishing the system simulation model (130) of the fluid network system according to the simulation models of each equipment and main pipe and the pipeline flow diagram includes: determining A proportional relationship between two variables, according to which the two variables are combined into one variable.
The optimization method (100) according to claim 1, characterized in that the objective function is system operating cost, the system operating cost includes fuel cost and operation and maintenance cost, and the optimal key parameters include main pipe temperature, Main pipe pressure, equipment power and equipment flow rate.
An optimization device (200) for a fluid network system, characterized in that the optimization device (200) includes:

The acquisition module (210) acquires the pipeline flow diagram of the fluid network system;

The modeling module (220) establishes a simulation model of each device and mother pipe in the fluid network system. The simulation model of each device and mother pipe includes a mechanism model and a data model;

The simulation module (230) establishes a system simulation model of the fluid network system based on the simulation models of each equipment and main pipe and the pipeline flow diagram;

Optimization module (240), establishes a system parameter optimization model according to the objective function and the system simulation model, uses the least squares method to solve the optimal key parameters of the system parameter optimization model, and runs the fluid according to the optimal key parameters Network Systems.
The optimization device (200) according to claim 6, characterized in that the simulation module (230) establishes a system simulation of the fluid network system based on the simulation models of each equipment and main pipe and the pipeline flow diagram. The model includes: establishing a graphical model of the pipeline flow chart, converting the graphical model into structured data, identifying the topology of the graphical model according to the structured data, using each of the equipment and motherboards. The simulation model of the tubes and the topology structure establish a system simulation model of the fluid network system.
The optimization device (200) according to claim 6 or 7, characterized in that the simulation module (230) establishes the fluid network system based on the simulation model of each equipment and main pipe and the pipeline flow diagram. The system simulation model includes: receiving a specified value of a variable input by the user, and replacing the variable in the system simulation model with the specified value.
The optimization device (200) according to claim 6, characterized in that the simulation module (230) establishes a system simulation of the fluid network system based on the simulation models of each equipment and main pipe and the pipeline flow diagram. The model includes determining a proportional relationship between two variables and merging the two variables into one variable based on the proportional relationship.
The optimization device (200) according to claim 6, characterized in that the objective function is system operating cost, the system operating cost includes fuel cost and operation and maintenance cost, and the optimal key parameters include main pipe temperature, Main pipe pressure, equipment power and equipment flow rate.
An electronic device (300), including a processor (310), a memory (320) and instructions stored in the memory (320), wherein the instructions when executed by the processor (310) implement as claimed The method described in any one of 1-5.
A computer-readable storage medium having computer instructions stored thereon which, when executed, perform the method according to any one of claims 1-5.