CN116108603B - Method for constructing wind tunnel air supply valve unit level information physical system - Google Patents
Method for constructing wind tunnel air supply valve unit level information physical system Download PDFInfo
- Publication number
- CN116108603B CN116108603B CN202310386811.9A CN202310386811A CN116108603B CN 116108603 B CN116108603 B CN 116108603B CN 202310386811 A CN202310386811 A CN 202310386811A CN 116108603 B CN116108603 B CN 116108603B
- Authority
- CN
- China
- Prior art keywords
- test
- supply valve
- air supply
- information
- pipeline
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/10—Geometric CAD
- G06F30/18—Network design, e.g. design based on topological or interconnect aspects of utility systems, piping, heating ventilation air conditioning [HVAC] or cabling
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M9/00—Aerodynamic testing; Arrangements in or on wind tunnels
- G01M9/02—Wind tunnels
- G01M9/04—Details
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M9/00—Aerodynamic testing; Arrangements in or on wind tunnels
- G01M9/06—Measuring arrangements specially adapted for aerodynamic testing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/16—Matrix or vector computation, e.g. matrix-matrix or matrix-vector multiplication, matrix factorization
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/28—Design optimisation, verification or simulation using fluid dynamics, e.g. using Navier-Stokes equations or computational fluid dynamics [CFD]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2111/00—Details relating to CAD techniques
- G06F2111/04—Constraint-based CAD
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2113/00—Details relating to the application field
- G06F2113/08—Fluids
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2113/00—Details relating to the application field
- G06F2113/14—Pipes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/14—Force analysis or force optimisation, e.g. static or dynamic forces
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Mathematical Analysis (AREA)
- Mathematical Physics (AREA)
- Geometry (AREA)
- Mathematical Optimization (AREA)
- Pure & Applied Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Computer Hardware Design (AREA)
- Computational Mathematics (AREA)
- Fluid Mechanics (AREA)
- Algebra (AREA)
- Software Systems (AREA)
- Computing Systems (AREA)
- Data Mining & Analysis (AREA)
- Medical Informatics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Artificial Intelligence (AREA)
- Computer Networks & Wireless Communication (AREA)
- Databases & Information Systems (AREA)
- Aerodynamic Tests, Hydrodynamic Tests, Wind Tunnels, And Water Tanks (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The present disclosure relates to a method for constructing a wind tunnel air supply valve unit level information physical system, which is used for wind tunnel test scheduling, and comprises: constructing an air source pipeline network model, and determining a pipeline communication adjacency matrix according to the air source pipeline network model; a sensing monitoring device is arranged at a gas supply valve of the gas source pipeline and is used for collecting state information of the gas supply valve; constructing a test information management system, which is used for acquiring basic data of test requirements, and determining a test requirement matrix at a plurality of moments according to test time sequences according to the basic data and a pipeline communication adjacent matrix; a power resource guarantee system is constructed and used for collecting the power resource stock information; and constructing a test scheduling intelligent system, which is used for determining opening and closing braking information of the air supply valve according to the test demand matrix, the air supply valve state information and the power resource stock information at a plurality of moments, and generating a valve operation instruction according to the opening and closing braking information so that the air supply valve is opened or closed according to the valve operation instruction at a test time sequence.
Description
Technical Field
The present disclosure relates generally to the field of wind tunnel testing, and more particularly, to a method for constructing a wind tunnel air supply valve unit level information physical system.
Background
The wind tunnel test is an aerodynamic experimental method for fixing an aircraft model in a wind tunnel, simulating various complex flight states of the aircraft in the air by artificially manufacturing airflow according to the relativity principle of motion, so as to obtain test data and know the aerodynamic characteristics of an actual aircraft.
The wind tunnel test scheduling is a resource guarantee plan which is developed around a specific scene of the wind tunnel test, is a complex system which relates to cooperation and interaction influence among people, objects, environments and resources, needs to correspondingly allocate a set of power resources for completing the wind tunnel test within a period of time, and belongs to the combination optimization problem. The wind tunnel test schedule may be dynamic or static. Dynamic scheduling is to determine the sequence of test jobs or tasks according to the current running environment state; static scheduling is typically pre-arranged, being the allocation of trial jobs or tasks from a given workflow.
The current wind tunnel test scheduling is still in a static scheduling mode, the test execution sequence is prearranged by means of a traditional manual organization mode, and along with the sudden increase of the test task quantity, the scheduling method is difficult to deal with the problems of emerging and uncertainty decision of a complex system, and the degree of automation and intelligence is relatively low.
Disclosure of Invention
The method for constructing the wind tunnel air supply valve unit level information physical system improves the automation and the intelligent degree of wind tunnel test scheduling, can deal with the problem of emerging and uncertainty decision of a complex system, and realizes the closed loop of sensing, analysis, decision making and execution.
In one general aspect, a method for constructing a wind tunnel air supply valve unit level information physical system is provided, and the method is used for wind tunnel test scheduling and comprises the following steps: constructing an air source pipeline network model according to the distribution condition of air source pipelines, and determining a pipeline communication adjacent matrix according to the air source pipeline network model; a sensing monitoring device is arranged at the air supply valve of the air supply pipeline and is used for collecting state information of the air supply valve; constructing a test information management system, which is used for acquiring basic data of test requirements, and determining a test requirement matrix at a plurality of moments according to test time sequences according to the basic data and the pipeline communication adjacent matrix; a power resource guarantee system is constructed and used for collecting the power resource stock information; and constructing a test scheduling intelligent system, which is used for determining opening and closing braking information of the air supply valve according to the test demand matrix, the air supply valve state information and the power resource stock information at a plurality of moments, and generating a valve operation instruction according to the opening and closing braking information so that the air supply valve is opened or closed according to the valve operation instruction under the test time sequence.
Optionally, the air source pipeline comprises a main pipeA line and a branch line, the pipeline communicating with the element q of the adjacency matrix ij ∈[1,0]Wherein q ij Indicating whether or not there is a branch line numbered j under the ith main line, when q ij When=1, it means that there is a branch line numbered j under the ith main line; when q ij When=0, it indicates that no branch line numbered j is present under the ith main line, where after the determining that the pipes communicate with the adjacency matrix, the method further includes: when q ij When=1, the maximum capacity upper limit c of the branch line numbered j under the ith main line is determined ij 。
Optionally, for any instant of the test requirement matrix, element d of the test requirement matrix ij Represents the power demand value of the branch line numbered j under the ith main line, where d ij ≤c ij 。
Optionally, the test scheduling intelligent system includes a pre-trained scheduling intelligent body, where determining, according to the test demand matrix at the multiple moments, the air supply valve state information, and the power resource inventory information, opening and closing braking information of the air supply valve includes: and inputting the test demand matrix, the air supply valve state information and the power resource stock information at a plurality of moments into the scheduling intelligent body so that the scheduling intelligent body predicts the opening and closing braking information of the air supply valve according to the test time sequence and generates the opening and closing braking information of the air supply valve at a plurality of moments.
Optionally, the scheduling agent trains well based on an objective function that maximizes the average utilization of the pipeline and minimizes the number of times the air supply power production system is turned on, and constraints that limit the upper power demand limit.
Optionally, the objective function is represented by the following equation:
，
，/>
wherein u is ij Represents the pipeline utilization, s, of the branch pipeline numbered j under the ith main pipeline ij The gas supply valve state of the branch line numbered j below the ith main line is represented, sum represents the total number of the branch lines, n represents the number of main lines, and Z represents the number of times the gas source power generation system is turned on.
Alternatively, s ij ∈[-1,0,1]Wherein, when s ij When=1, the branch line numbered j below the ith main line is in an open state; when s is ij When=0, it means that the branch line numbered j under the ith main line is in the closed state; when s is ij When = -1, it indicates that there is no branch line numbered j under the i-th main line or that the open/close state of the branch line numbered j under the i-th main line is invalid.
Optionally, the constraint is expressed by the following equation:
wherein P represents the total power production of the air source, < >>
Indicating the lower limit value of the air source power.
Optionally, the air supply piping network model is represented by a capacity directed graph G (V, E, C), where V represents a set of vertices, E represents a set of edges, and C represents an upper maximum capacity limit that each edge is allowed to allocate.
Optionally, after the setting the sensing and monitoring device, the method further includes: and constructing a standard data interface according to the object link and the embedded process control standard, wherein the standard data interface is used for unifying data access modes of different sensing monitoring devices, so that the test scheduling intelligent system can acquire the state information of the air supply valve acquired by the sensing monitoring devices through the standard data interface.
According to the method for constructing the wind tunnel air supply valve unit level information physical system, which is disclosed by the embodiment of the invention, four stages of construction of the information physical system are covered, and an effective closed loop from state sensing, real-time analysis and autonomous decision to accurate execution is formed, so that an intelligent system for opening and closing the wind tunnel air supply valve based on test scheduling is formed, the artificial misoperation is effectively reduced, and the energy consumption when power resource supply optimization is not considered is reduced; specifically, an information physical system is constructed aiming at the specific operation of valve opening and closing of a main pipeline and a branch pipeline in a wind tunnel air source system, an information closed loop taking knowledge as a core is formed, the method can help testers to realize the knowledge, the measurability, the optimality and the controllability of air source supply conditions in the test process, the maximum utilization rate of power resources and the minimum opening and closing times of a power production system are realized as optimization targets, the test scheduling execution time sequence in the whole domain range is predicted, the opening or closing action prediction of the main pipeline and the branch pipeline of the air source is executed according to the prediction time in the test execution process in combination with an operation instruction, the pressure is regulated by taking the test demand as the valve opening degree, and the closed loop of sensing, analysis, decision and execution is realized.
Additional aspects and/or advantages of the present general inventive concept will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the general inventive concept.
Drawings
The foregoing and other objects and features of embodiments of the present disclosure will become more apparent from the following description taken in conjunction with the accompanying drawings in which the embodiments are shown, in which:
FIG. 1 is a schematic diagram illustrating a wind tunnel main intake pipe and valve system according to an embodiment of the present disclosure;
FIG. 2 is a flow chart illustrating a method of constructing a wind tunnel air supply valve unit level information physical system according to an embodiment of the present disclosure;
FIG. 3 is a schematic diagram illustrating a gas source piping network model according to an embodiment of the present disclosure;
FIG. 4 is a schematic diagram illustrating a pipe communication adjacency matrix according to an embodiment of the present disclosure;
FIG. 5 is a schematic diagram illustrating wind tunnel valve information acquisition according to an embodiment of the present disclosure;
FIG. 6 is a schematic diagram illustrating a test demand matrix at a certain time in accordance with an embodiment of the present disclosure;
FIG. 7 is a schematic diagram illustrating scheduling agent interaction with environmental information, according to an embodiment of the present disclosure;
fig. 8 is a schematic diagram illustrating the construction of a gas supply valve unit level information physical system according to an embodiment of the present disclosure.
Detailed Description
The following detailed description is provided to assist the reader in obtaining a thorough understanding of the methods, apparatus, and/or systems described herein. However, various changes, modifications, and equivalents of the methods, apparatuses, and/or systems described herein will be apparent after an understanding of the disclosure of the present application. For example, the order of operations described herein is merely an example and is not limited to those set forth herein, but may be altered as will be apparent after an understanding of the disclosure of the present application, except for operations that must occur in a particular order. Furthermore, descriptions of features known in the art may be omitted for clarity and conciseness.
The features described herein may be embodied in different forms and should not be construed as limited to the examples described herein. Rather, the examples described herein have been provided to illustrate only some of the many possible ways to implement the methods, devices, and/or systems described herein, which will be apparent after an understanding of the present disclosure.
Unless defined otherwise, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this disclosure belongs after understanding this disclosure. Unless explicitly so defined herein, terms (such as those defined in a general dictionary) should be construed to have meanings consistent with their meanings in the context of the relevant art and the present disclosure, and should not be interpreted idealized or overly formal.
In addition, in the description of the examples, when it is considered that detailed descriptions of well-known related structures or functions will cause a ambiguous explanation of the present disclosure, such detailed descriptions will be omitted.
The wind tunnel is a pipeline-shaped test device, is one of the most commonly used and effective tools for performing aerodynamic tests, and mainly comprises a plurality of parts such as an air source and vacuum system, a pipeline and valve system, a test section, a measurement and control system and the like. The air source system can be designed together with the wind tunnel monomer as a power system of the wind tunnel, adopts a self-sufficient independent guarantee mode, can also be independently and separately designed with the wind tunnel monomer, and adopts a centralized guarantee mode to realize air source supply. By way of example, the air supply system referred to in this disclosure is in a centralized supply assurance mode.
FIG. 1 is a schematic diagram illustrating a wind tunnel main intake pipe and valve system according to an embodiment of the present disclosure. As shown in figure 1, a control valve is arranged between the main air inlet pipeline and the branch pipeline and can be controlled by a 0/1 signal, and the wind tunnel monomer is mainly composed of three valves, namely a safety valve, a quick valve and a pressure regulating valve. The safety valve is usually a gate valve, is a first barrier for air flow to enter the wind tunnel main body, can be controlled by 0/1, is in an open state in the normal test process, and is in a closed state only when the wind tunnel maintenance and guarantee task is executed; the quick valve is usually a butterfly valve, is a second barrier for air flow to enter the wind tunnel main body, can be controlled by 0/1, and is opened after wind tunnel test is ready; the pressure regulating valve usually adopts an annular gap valve, a position sensor is arranged in the pressure regulating valve, and the pressure change of the air pressure in front of and behind the valve is controlled to determine the air inlet pressure of the test section. Pressure regulating valves typically can control regulated pressure dynamically and continuously.
A method of constructing a wind tunnel air supply valve unit level information physical system according to an embodiment of the present disclosure will be described in detail with reference to fig. 2 to 8.
Fig. 2 is a flowchart illustrating a method of constructing a wind tunnel air supply valve unit level information physical system according to an embodiment of the present disclosure.
Referring to fig. 2, in step S201, an air source pipeline network model may be constructed according to the distribution situation of air source pipelines, and a pipeline communication adjacency matrix may be determined according to the air source pipeline network model. Here, the gas source piping may include a main line and a branch line. In one possible implementation, the air supply piping network model may be represented by a capacity directed graph G (V, E, C), where V represents a set of vertices, E represents a set of edges, and C represents an upper maximum capacity limit that each edge is allowed to allocate.
Fig. 3 is a schematic diagram illustrating a gas source piping network model according to an embodiment of the present disclosure.
Referring to FIG. 3, the air source pipeline network may comprise wind tunnel test power resources D, sink nodes D1-D12 and wind tunnel test bodies wt-01-wt-26. Here, the wind tunnel test power resource D and the sink nodes D1-D12 are connected through main pipelines 1-12#, and the sink nodes D1-D12 and wind tunnel test bodies wt-01-wt-26 are connected through branch pipelines 1-26. Further, the wind tunnel test power resource is used for producing and storing the power resource for providing air flow for the wind tunnel test. Further, some main pipelines are connected with branch pipelines, while other main pipelines are not connected with branch pipelines, as shown in figure 3, branch pipelines are connected to main pipelines 1#, 4#, 5#, 7#, 8#, 9#, 10#, 12#, and branch pipelines are not connected to main pipelines 2#, 3#, 6#, 11#; in addition, the number of branch lines connected to the main line may be different, as shown in fig. 3, 3 branch lines are connected to the main line 1 # and 8 branch lines are connected to the main line 5 #.
For convenience in describing the main and branch lines in the gas source piping network model, the subscript ij in the embodiments of the present disclosure indicates that a branch line numbered j may exist under the ith main line, as shown in fig. 3, when i= 5,j =7, indicates that a branch line numbered 7 exists under the 5 th main line, that is, a branch line 7 under the main line 5+.
To mathematical the gas source piping network model, a piping connectivity adjacency matrix Q may be determined. Here, the pipeline communicates with the element Q of the adjacency matrix Q ij ∈[1,0]Wherein q ij Indicating whether or not there is a branch line numbered j under the ith main line, when q ij When=1, it means that there is a branch line numbered j under the ith main line; when q ij When=0, it means that there is no branch line numbered j below the ith main line.
Thus, the pipeline communication adjacency matrix of the air source pipeline network model shown in fig. 3 is shown in fig. 4. Fig. 4 is a schematic diagram illustrating a pipe communication adjacency matrix according to an embodiment of the present disclosure.
Referring to FIG. 4, q 5 6 ~q 5 13 All are equal to 1, namely, the existence of branch pipelines with the numbers of 6-13 under the 5 th main pipeline is indicated; similarly, q 9 21 ~q 9 26 All equal to 0, which means that no branch lines with numbers 21-26 exist under the 9 th main pipeline.
Through the pipeline communication adjacent matrix, the communication relation of the air source pipeline network model is subjected to mathematical characteristic description, and the air source pipeline network model is visual and clear.
According to an embodiment of the present disclosure, after determining the pipe-connected adjacency matrix, when q ij When=1, the maximum capacity upper limit c of the branch line numbered j under the ith main line can also be determined ij . Here, the maximum capacity upper limit is determined according to the maximum bearing capacity of the pipeline, and is used for restricting the air source requirement of the single wind tunnel monomer so as to enable the prediction result in the follow-up test scheduling to be more reasonable and accurate.
Referring back to fig. 2, next, in step S202, a sensing and monitoring device may be provided at the air supply valve of the air supply pipe for collecting air supply valve status information. Here, after the sensor monitoring device is set, a standard data interface may be constructed according to the object linking and embedded process control (OLE for Process Control, OPC) standard, for unifying data access modes of different sensor monitoring devices, so that an experimental scheduling intelligent system to be described later acquires the status information of the air supply valve collected by the sensor monitoring device through the standard data interface.
Fig. 5 is a schematic diagram illustrating wind tunnel valve information acquisition according to an embodiment of the present disclosure. After the acquisition is carried out through the sensing monitoring device, an open standard data interface is defined by using an OPC standard, and on the interface, a PC-based software component can exchange data, and the data can be accessed in a unified mode no matter what form the field equipment exists, so that the seamless transmission of information among equipment of different manufacturers is realized.
Referring back to fig. 2, next, in step S203, a test information management system may be constructed, for acquiring basic data of a test requirement, and determining a test requirement matrix at a plurality of moments according to a test time sequence according to the basic data and a pipeline connection adjacency matrix. Here, a requirement collection page can be configured on the test information management system, so that uploading, collection and summarization of test requirements are carried out by relying on the requirement collection page to serve as basic data of power resource allocation; and then, abstracting the test requirements according to the pipeline communication adjacent matrix to be combined in the air source pipeline network to form a test requirement matrix D at a plurality of moments.
According to an embodiment of the present disclosure, for any instant of the test requirement matrix, element d of the test requirement matrix ij The power demand value of the branch line numbered j under the ith main line is expressed, and the unit of the power demand value may be megapascals (MPa). Here, when d ij When=0, it means that there is no branch line numbered j under the i-th main line or there is no power demand for the branch line numbered j under the i-th main line; when d ij >At 0, the branch line numbered j below the ith main line is powered. Note that d ij ≤c ij I.e. the power demand value of a single branch line should be less than the maximum capacity upper limit of that branch line.
Fig. 6 is a schematic diagram illustrating a test demand matrix at a certain time according to an embodiment of the present disclosure.
Reference is made to figure 6,D 5 6 Equal to 3, namely, the branch line numbered 6 below the 5 th main pipeline has a power requirement, and the power requirement value is 3; similarly, D 9 21 Equal to 0, meaning that no branch line number 21 is present under the 9 th main line or no power demand is present under the 9 th main line for the branch line number 21.
Through the test demand matrix, mathematical characteristic description is carried out on test demand basic data at a certain moment, and the test demand matrix is visual and clear.
Referring back to fig. 2, next, in step S204, a power resource securing system may be constructed for collecting power resource inventory information. Here, the power resource inventory information may include air supply reserve information, power production and consumption information, etc., which the present disclosure does not limit.
Next, in step S205, a test scheduling intelligent system may be constructed, for determining opening and closing braking information of the air supply valve according to the test demand matrix, the air supply valve state information and the power resource stock information at a plurality of moments, and generating a valve operation instruction according to the opening and closing braking information, so that the air supply valve is opened or closed according to the valve operation instruction under the test time sequence.
Fig. 7 is a schematic diagram illustrating scheduling agent interaction with environmental information according to an embodiment of the present disclosure.
As an example, a test scheduling intelligent algorithm may be established, a Markov Decision Process (MDP) is used to collect and monitor environmental information consisting of test requirement information (matrix) related to test scheduling, air supply valve (opening and closing) state information and power resource stock (air supply) information in real time, as an input condition of the test intelligent scheduling algorithm, a reinforcement learning algorithm is used, and opening and closing brake information of a main pipeline and a branch pipeline valve is obtained through interaction of the test scheduling state and the environmental information as output.
In one possible implementation, the test scheduling intelligent system may include a pre-trained scheduling intelligent agent, so that the test demand matrix, the air supply valve state information and the power resource inventory information at a plurality of moments may be input into the scheduling intelligent agent, so that the scheduling intelligent agent predicts the opening and closing braking information of the air supply valve according to the test time sequence, and generates the opening and closing braking information of the air supply valve at a plurality of moments. Here, the scheduling agent may train well based on an objective function that maximizes the average utilization of the pipeline and minimizes the number of times the air supply power production system is turned on, as well as constraints that limit the upper power demand limit.
According to an embodiment of the present disclosure, the objective function may be represented by the following equations (1), (2) and (3):
here, u ij Represents the pipeline utilization, s, of the branch pipeline numbered j under the ith main pipeline ij The gas supply valve state of the branch line numbered j below the ith main line is represented, sum represents the total number of the branch lines, n represents the number of main lines, and Z represents the number of times the gas source power generation system is turned on. Further, s ij ∈[-1,0,1]When s is ij When=1, the branch line numbered j below the ith main line is in an open state; when s is ij When=0, it means that the branch line numbered j under the ith main line is in the closed state; when s is ij When = -1, it indicates that there is no branch line numbered j under the i-th main line or that the open/close state of the branch line numbered j under the i-th main line is invalid. It should be noted that in the case where the open/close state of the branch line numbered j under the ith main line is invalid, it is indicated that the constructed system is in error in operation, and the corresponding calculation can be performed again after the error is checked.
In addition, the constraints limiting the upper power demand limit may include a demand constraint, a pipeline upper limit constraint, and a system turn-on number constraint, the demand constraint indicating that the sum of the wind tunnel monomer air source demands cannot be greater than the total air source power output, the pipeline upper limit constraint indicating that the individual wind tunnel monomer air source demands cannot be greater than the maximum pipeline load, the system turn-on number constraint indicating that the number of times the air source power production system is turned on varies with time according to the condition of the total air source power output. As an example, the constraint is represented by the following equation (4):
here, P represents the total power output of the air source,
indicating the lower limit value of the air source power. Further, the method comprises the steps of,
is indicated at->
In the case of (2), the number of times the air source power production system is turned on is increased by 1 in the next time step. It should be appreciated that training of intelligent agents may be performed during a time of day based on the objective functions and constraints described above, which may be divided into a plurality of time steps, the duration of each of which may be set by one of ordinary skill in the art depending on the actual situation, as this disclosure is not limited.
For a better understanding of the above-described embodiments of the present disclosure, a description is given below in conjunction with fig. 8. Fig. 8 is a schematic diagram illustrating the construction of a gas supply valve unit level information physical system according to an embodiment of the present disclosure.
By way of example, the test task demand in a certain time period is taken as a main line, the real-time monitored power resource storage capacity change is taken as an allocation reference, the upper limit capacity of the air supply pipeline is taken as a limiting condition, and the test scheduling time and the test queuing sequence in the whole domain range are intelligently predicted, so that the test scheduling time and the test queuing sequence are further converted into command signals for opening and closing the air supply valve of the air source in a specified time for a certain wind tunnel monomer, and a wind tunnel air supply valve unit level information physical system based on the test scheduling is constructed.
As shown in fig. 8, a sensing monitoring device can be set at a single air supply valve switch of a wind tunnel based on an equipment maintenance support platform to serve as a switch detection point, test requirements are submitted to a test management system aiming at a single air supply valve switch of a certain wind tunnel, the test management system collects the test requirements of each single air supply valve switch of the wind tunnel, then the test management system sends the comprehensive test requirements to a power resource support system, the power resource support system combines the information such as pipeline states collected from an air source pipeline network model, and the like, the collected information is sent to a test scheduling intelligent system for comprehensive analysis, and the test scheduling intelligent system sends a valve operation instruction to open or close the valve switch of a centralized air source supply point or the single air supply valve switch of the certain wind tunnel according to analysis results.
According to the method for constructing the wind tunnel air supply valve unit level information physical system, which is disclosed by the embodiment of the invention, four stages of construction of the information physical system are covered, and an effective closed loop from state sensing, real-time analysis and autonomous decision to accurate execution is formed, so that an intelligent system for opening and closing the wind tunnel air supply valve based on test scheduling is formed, the artificial misoperation is effectively reduced, and the energy consumption when power resource supply optimization is not considered is reduced; specifically, an information physical system is constructed aiming at the specific operation of valve opening and closing of a main pipeline and a branch pipeline in a wind tunnel air source system, an information closed loop taking knowledge as a core is formed, the method can help testers to realize the knowledge, the measurability, the optimality and the controllability of air source supply conditions in the test process, the maximum utilization rate of power resources and the minimum opening and closing times of a power production system are realized as optimization targets, the test scheduling execution time sequence in the whole domain range is predicted, the opening or closing action prediction of the main pipeline and the branch pipeline of the air source is executed according to the prediction time in the test execution process in combination with an operation instruction, the pressure is regulated by taking the test demand as the valve opening degree, and the closed loop of sensing, analysis, decision and execution is realized.
Although a few embodiments of the present disclosure have been shown and described, it would be appreciated by those skilled in the art that changes may be made in these embodiments without departing from the principles and spirit of the disclosure, the scope of which is defined in the claims and their equivalents.
Claims (6)
1. The method for constructing the wind tunnel air supply valve unit level information physical system is used for wind tunnel test scheduling and is characterized by comprising the following steps:
constructing an air source pipeline network model according to the distribution condition of air source pipelines, and determining a pipeline communication adjacent matrix according to the air source pipeline network model;
a sensing monitoring device is arranged at the air supply valve of the air supply pipeline and is used for collecting state information of the air supply valve;
constructing a test information management system, which is used for acquiring basic data of test requirements, and determining a test requirement matrix at a plurality of moments according to test time sequences according to the basic data and the pipeline communication adjacent matrix;
a power resource guarantee system is constructed and used for collecting the power resource stock information;
constructing a test scheduling intelligent system, which is used for determining opening and closing braking information of the air supply valve according to the test demand matrix, the air supply valve state information and the power resource stock information at a plurality of moments, and generating a valve operation instruction according to the opening and closing braking information so that the air supply valve is opened or closed according to the valve operation instruction at the test time sequence;
for any moment in time, the element d of the test requirement matrix ij Represents the power demand value of the branch line numbered j under the ith main line, where d ij ≤c ij ，c ij An upper limit of the maximum capacity of a branch line numbered j adjacent to the ith main line;
the test scheduling intelligent system comprises a pre-trained scheduling intelligent body, wherein the scheduling intelligent body is trained based on an objective function of maximizing the average utilization rate of a pipeline and minimizing the starting times of an air source power production system and a constraint condition of limiting the upper limit of the power demand;
the constraint is represented by the following equation:
wherein P represents the total power output of the air source,
the lower limit value of the air source power is represented, n represents the number of main pipelines, Z represents the number of times of opening the air source power production system, and Sum represents the total number of branch pipelines;
the air supply piping network model is represented by a capacity directed graph G (V, E, C), where V represents a set of vertices, E represents a set of edges, and C represents an upper maximum capacity limit that each edge is allowed to allocate.
2. The method of construction according to claim 1, wherein the gas source conduit comprises a main conduit and a branch conduit, the conduit communicating with the element q of the adjacency matrix ij ∈[1,0]Wherein q ij Indicating whether or not there is a branch line numbered j under the ith main line, when q ij When=1, it means that there is a branch line numbered j under the ith main line; when q ij When=0, it means that there is no branch line numbered j under the ith main line,
wherein after determining the pipe communication adjacency matrix, further comprising:
when q ij When=1, the maximum capacity upper limit c of the branch line numbered j under the ith main line is determined ij 。
3. The construction method according to claim 2, wherein the determining the opening/closing brake information of the air supply valve based on the test demand matrix, the air supply valve state information, and the power resource inventory information at the plurality of times includes:
and inputting the test demand matrix, the air supply valve state information and the power resource stock information at a plurality of moments into the scheduling intelligent body so that the scheduling intelligent body predicts the opening and closing braking information of the air supply valve according to the test time sequence and generates the opening and closing braking information of the air supply valve at a plurality of moments.
4. A construction method according to claim 3, wherein the objective function is represented by the following equation:
wherein u is ij Represents the pipeline utilization, s, of the branch pipeline numbered j under the ith main pipeline ij The gas supply valve state of the branch line numbered j under the ith main line.
5. The method of construction of claim 4 wherein s ij ∈[-1,0,1]Wherein, when s ij When=1, the branch line numbered j below the ith main line is in an open state; when s is ij When=0, it means that the branch line numbered j under the ith main line is in the closed state; when s is ij When = -1, it indicates that there is no branch line numbered j under the i-th main line or that the open/close state of the branch line numbered j under the i-th main line is invalid.
6. The construction method according to any one of claims 1 to 5, further comprising, after the setting of the sensor monitoring device:
and constructing a standard data interface according to the object link and the embedded process control standard, wherein the standard data interface is used for unifying data access modes of different sensing monitoring devices, so that the test scheduling intelligent system can acquire the state information of the air supply valve acquired by the sensing monitoring devices through the standard data interface.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310386811.9A CN116108603B (en) | 2023-04-12 | 2023-04-12 | Method for constructing wind tunnel air supply valve unit level information physical system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310386811.9A CN116108603B (en) | 2023-04-12 | 2023-04-12 | Method for constructing wind tunnel air supply valve unit level information physical system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116108603A CN116108603A (en) | 2023-05-12 |
| CN116108603B true CN116108603B (en) | 2023-06-27 |
Family
ID=86256561
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310386811.9A Active CN116108603B (en) | 2023-04-12 | 2023-04-12 | Method for constructing wind tunnel air supply valve unit level information physical system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116108603B (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111737886A (en) * | 2020-08-07 | 2020-10-02 | 中国空气动力研究与发展中心低速空气动力研究所 | Wind tunnel test scheduling method and system |
| CN111738627A (en) * | 2020-08-07 | 2020-10-02 | 中国空气动力研究与发展中心低速空气动力研究所 | Wind tunnel test scheduling method and system based on deep reinforcement learning |
| CN114692524A (en) * | 2022-03-31 | 2022-07-01 | 中国空气动力研究与发展中心计算空气动力研究所 | Wind tunnel group high-pressure air resource dynamic topological structure modeling method and system and air consumption calculation |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11430581B2 (en) * | 2017-10-05 | 2022-08-30 | Maxell, Ltd. | Contactless infernal measurement device, contactless internal measurement method, and internal measurement result display system |
-
2023
- 2023-04-12 CN CN202310386811.9A patent/CN116108603B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111737886A (en) * | 2020-08-07 | 2020-10-02 | 中国空气动力研究与发展中心低速空气动力研究所 | Wind tunnel test scheduling method and system |
| CN111738627A (en) * | 2020-08-07 | 2020-10-02 | 中国空气动力研究与发展中心低速空气动力研究所 | Wind tunnel test scheduling method and system based on deep reinforcement learning |
| CN114692524A (en) * | 2022-03-31 | 2022-07-01 | 中国空气动力研究与发展中心计算空气动力研究所 | Wind tunnel group high-pressure air resource dynamic topological structure modeling method and system and air consumption calculation |
Non-Patent Citations (3)
| Title |
|---|
| 基于CPS的气动试验研究体系全链路数据融合研究;何福;罗昌俊;马永一;汤瀑;;计算机测量与控制(第07期);第269-273页 * |
| 基于S7-300 PLC的高超声速高温风洞控制系统设计;蒲旭阳;胡俊逸;李向东;邓和平;卢传喜;;自动化与仪表(第10期);第45-48页 * |
| 高空模拟试验应急管理的Petri网建模及应用;马锋;邱菀华;;北京航空航天大学学报(第10期);第1207-1212页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116108603A (en) | 2023-05-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110866592B (en) | Model training method, device, energy efficiency prediction method, device and storage medium | |
| CN101448267A (en) | Wireless sensor network node coverage optimization method based on particle swarm algorithm | |
| CN105512448A (en) | Power distribution network health index assessment method | |
| EP3985460B1 (en) | Controller, control system and method to control a facility and to generate a control model by learning | |
| CN114564000B (en) | Active fault tolerance method and system based on intelligent aircraft actuator fault diagnosis | |
| CN110826784B (en) | Method and device for predicting energy use efficiency, storage medium and terminal equipment | |
| CN111737886B (en) | Wind tunnel test scheduling method and system | |
| CN109255726A (en) | A kind of ultra-short term wind power prediction method of Hybrid Intelligent Technology | |
| CN109977621A (en) | A kind of air-conditioning failure prediction method based on deep learning | |
| Li et al. | Framework and case study of cognitive maintenance in Industry 4.0 | |
| CN113606634A (en) | Heat source guarantee system based on long-distance transmission pipe network optimization heat source operation parameter | |
| CN114119273A (en) | Park comprehensive energy system non-invasive load decomposition method and system | |
| CN116108603B (en) | Method for constructing wind tunnel air supply valve unit level information physical system | |
| CN111626003A (en) | Heating system heat load layered prediction method, storage medium and prediction equipment | |
| CN117690563A (en) | Intelligent instrument distribution system of shelter hospital | |
| CN111738627B (en) | Wind tunnel test scheduling method and system based on deep reinforcement learning | |
| CN117812123A (en) | Valve regulation and control method and system based on Internet of things | |
| CN116520074A (en) | Active power distribution network fault positioning method and system based on cloud edge cooperation | |
| CN112821456B (en) | Distributed source-storage-load matching method and device based on transfer learning | |
| CN114552570A (en) | Offshore wind power prediction management system | |
| CN114897196B (en) | Operation management method, equipment and medium for office building water supply network | |
| CN113269435B (en) | New energy station running state coupling monitoring and evaluating system | |
| Ming et al. | Intelligent Opening and Closing Braking Method for Wind Tunnel Air Source Valves based on CPS | |
| Lu et al. | Elevator Error Diagnosis Method Based on Neural Network Model | |
| KR102554902B1 (en) | The Method that Estimate Energy Consumption of Group Households based on Federated Learning, and The System and Computer-readable Medium for Performing The Same |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |