CN117034654A - Virtual simulation system generation method based on refrigerating system and related equipment - Google Patents
Virtual simulation system generation method based on refrigerating system and related equipment Download PDFInfo
- Publication number
- CN117034654A CN117034654A CN202311113858.4A CN202311113858A CN117034654A CN 117034654 A CN117034654 A CN 117034654A CN 202311113858 A CN202311113858 A CN 202311113858A CN 117034654 A CN117034654 A CN 117034654A
- Authority
- CN
- China
- Prior art keywords
- model
- equipment
- refrigeration
- data
- ith
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 95
- 238000005057 refrigeration Methods 0.000 claims abstract description 416
- 238000011144 upstream manufacturing Methods 0.000 claims abstract description 105
- 239000012530 fluid Substances 0.000 claims abstract description 89
- 238000005094 computer simulation Methods 0.000 claims abstract description 33
- 238000013461 design Methods 0.000 claims description 81
- 238000012795 verification Methods 0.000 claims description 52
- 238000004088 simulation Methods 0.000 claims description 43
- 238000012545 processing Methods 0.000 claims description 37
- 238000003860 storage Methods 0.000 claims description 30
- 230000003993 interaction Effects 0.000 claims description 29
- 230000008859 change Effects 0.000 claims description 28
- 230000008569 process Effects 0.000 claims description 25
- 238000001514 detection method Methods 0.000 claims description 20
- 238000005538 encapsulation Methods 0.000 claims description 16
- 238000012937 correction Methods 0.000 claims description 6
- 230000001419 dependent effect Effects 0.000 claims description 5
- 230000002159 abnormal effect Effects 0.000 claims description 4
- 238000012216 screening Methods 0.000 claims description 4
- 238000001816 cooling Methods 0.000 description 60
- 239000000498 cooling water Substances 0.000 description 59
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 58
- 238000007710 freezing Methods 0.000 description 23
- 230000008014 freezing Effects 0.000 description 23
- 238000004422 calculation algorithm Methods 0.000 description 21
- 230000006870 function Effects 0.000 description 16
- 238000005265 energy consumption Methods 0.000 description 14
- 238000004590 computer program Methods 0.000 description 11
- 230000009471 action Effects 0.000 description 10
- 238000004806 packaging method and process Methods 0.000 description 9
- 238000011161 development Methods 0.000 description 7
- 238000010586 diagram Methods 0.000 description 7
- 238000005457 optimization Methods 0.000 description 6
- 238000005516 engineering process Methods 0.000 description 5
- 238000012546 transfer Methods 0.000 description 5
- 238000013459 approach Methods 0.000 description 4
- 238000013473 artificial intelligence Methods 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 4
- 230000008901 benefit Effects 0.000 description 3
- 238000006243 chemical reaction Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 238000007726 management method Methods 0.000 description 3
- 238000012360 testing method Methods 0.000 description 3
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 description 2
- 229910052799 carbon Inorganic materials 0.000 description 2
- 230000004069 differentiation Effects 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 239000000203 mixture Substances 0.000 description 2
- 238000003062 neural network model Methods 0.000 description 2
- 239000003507 refrigerant Substances 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000015556 catabolic process Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 238000006731 degradation reaction Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 238000004134 energy conservation Methods 0.000 description 1
- 230000009969 flowable effect Effects 0.000 description 1
- 230000017525 heat dissipation Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000013178 mathematical model Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000013508 migration Methods 0.000 description 1
- 230000005012 migration Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000006386 neutralization reaction Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 239000004984 smart glass Substances 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 230000001052 transient effect Effects 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
Classifications
-
- 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
-
- 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
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/08—Thermal analysis or thermal optimisation
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Hardware Design (AREA)
- Evolutionary Computation (AREA)
- Geometry (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Air Conditioning Control Device (AREA)
Abstract
The application discloses a virtual simulation system generation method based on a refrigerating system and related equipment, wherein the method comprises the following steps: performing simulation modeling on each refrigeration device in a refrigeration system to obtain an initial device model corresponding to each refrigeration device; determining upstream and downstream boundary conditions of a corresponding initial equipment model according to physical information of upstream and downstream fluids of each refrigeration equipment; identifying and calibrating model parameters of the corresponding initial equipment model based on operation data generated by the histories of the refrigeration equipment and upstream and downstream boundary conditions of the corresponding initial equipment model respectively to obtain a target equipment model corresponding to the refrigeration equipment; according to the equipment configuration information of the refrigeration system, connecting the target equipment models corresponding to the refrigeration equipment to obtain a virtual simulation system corresponding to the refrigeration system; by the method and the device, a more accurate virtual simulation system can be automatically generated.
Description
Technical Field
The application relates to the technical field of Internet, in particular to the technical field of artificial intelligence, and particularly relates to a virtual simulation system generation method based on a refrigerating system and related equipment.
Background
With the development of internet technology, data centers become a key infrastructure supporting emerging technologies such as cloud computing, digitization, metauniverse, artificial intelligence (Artificial Intelligence, AI), and the like. With the development and wide application of related technologies, data centers are built well; along with this, the energy consumption is also increasing. Because of the large amount of heat dissipation in the working process of the chip, a large part of energy consumption of the data center is consumed in the corresponding refrigerating system, so that the reduction of the energy consumption of the refrigerating system of the data center has important significance for improving the running economy of the data center and assisting in the carbon peak and the carbon neutralization of the data center.
At present, an AI energy-saving algorithm is generally utilized to reduce the energy consumption of a refrigeration system; however, as an optimization method depending on data and trial and error, the AI energy-saving algorithm itself also needs to be debugged and optimized. If the AI energy-saving algorithm is directly deployed in a real refrigeration system for debugging and optimizing, the following problems exist: (1) high costs (such as labor costs, time costs, and hardware and software deployment costs) are consumed, (2) reliable operation of the refrigeration system is affected due to the possible presence of a corercase and unknown bug before the AI power saving algorithm debug optimization is complete. The virtual simulation system can effectively solve the two problems, namely, the AI energy-saving algorithm is debugged and optimized on the virtual simulation system corresponding to the refrigeration system, so that the cost and the running risk can be effectively reduced. Based on this, how to generate a virtual simulation system corresponding to a refrigeration system becomes a current research hotspot.
Disclosure of Invention
The embodiment of the application provides a virtual simulation system generation method based on a refrigeration system and related equipment, which can automatically generate a more accurate virtual simulation system aiming at the refrigeration system.
In one aspect, an embodiment of the present application provides a method for generating a virtual simulation system based on a refrigeration system, where the method includes:
performing simulation modeling on each refrigeration device in a refrigeration system to obtain an initial device model corresponding to each refrigeration device, wherein one refrigeration device corresponds to one initial device model;
respectively acquiring the upstream and downstream boundary conditions of each initial equipment model, wherein the upstream and downstream boundary conditions of any initial equipment model are determined according to the physical information of upstream and downstream fluid of corresponding refrigeration equipment; wherein the upstream and downstream boundary conditions of the initial equipment model include: information required to run the corresponding initial equipment model;
identifying and calibrating model parameters of the corresponding initial equipment model based on operation data generated by the histories of the refrigeration equipment and upstream and downstream boundary conditions of the corresponding initial equipment model respectively to obtain a target equipment model corresponding to the refrigeration equipment;
And connecting the target equipment models corresponding to the refrigeration equipment according to the equipment configuration information of the refrigeration system to obtain a virtual simulation system corresponding to the refrigeration system.
In another aspect, an embodiment of the present application provides a virtual simulation system generating apparatus based on a refrigeration system, where the apparatus includes:
the modeling unit is used for performing simulation modeling on each refrigeration device in the refrigeration system to obtain an initial device model corresponding to each refrigeration device, wherein one refrigeration device corresponds to one initial device model;
the processing unit is used for respectively acquiring the upstream and downstream boundary conditions of each initial equipment model, and the upstream and downstream boundary conditions of any initial equipment model are determined according to the physical information of upstream and downstream fluid of the corresponding refrigeration equipment; wherein the upstream and downstream boundary conditions of the initial equipment model include: information required to run the corresponding initial equipment model;
the processing unit is further used for identifying and calibrating model parameters of the corresponding initial equipment model based on operation data generated by histories of the refrigeration equipment and upstream and downstream boundary conditions of the corresponding initial equipment model respectively to obtain a target equipment model corresponding to the refrigeration equipment;
And the processing unit is also used for connecting the target equipment models corresponding to the refrigeration equipment according to the equipment configuration information of the refrigeration system to obtain a virtual simulation system corresponding to the refrigeration system.
In yet another aspect, an embodiment of the present application provides a computer device, including an input interface and an output interface, the computer device further including:
a processor and a computer storage medium;
wherein the processor is adapted to implement one or more instructions, the computer storage medium storing one or more instructions adapted to be loaded by the processor and to perform the above-mentioned refrigeration system-based virtual simulation system generation method.
In yet another aspect, embodiments of the present application provide a computer storage medium storing one or more instructions adapted to be loaded by a processor and to perform the above-mentioned refrigeration system-based virtual simulation system generation method.
In yet another aspect, embodiments of the present application provide a computer program product comprising one or more instructions; the one or more instructions in the computer program product, when executed by the processor, implement the refrigeration system-based virtual simulation system generation method mentioned above.
According to the embodiment of the application, simulation modeling can be carried out on each refrigeration device in the refrigeration system to obtain the initial device model corresponding to each refrigeration device, physical information of upstream and downstream fluid of each refrigeration device is respectively obtained, the determined upstream and downstream boundary conditions of the corresponding initial device model are used for ensuring that each initial device model can normally operate based on the obtained upstream and downstream boundary conditions, so that model parameters of the corresponding initial device model can be identified and calibrated based on operation data generated by histories of each refrigeration device and the upstream and downstream boundary conditions of the corresponding initial device model respectively to obtain the target device model corresponding to each refrigeration device, the operation state of the corresponding refrigeration device can be accurately reflected by each target device model, the self-adaptive characteristic is realized, and a relatively accurate virtual simulation system can be automatically generated by connecting each target device.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for the description of the embodiments will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present application, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1a is a schematic diagram of a refrigeration system according to an embodiment of the present application;
FIG. 1b is a schematic flow chart of a virtual simulation system generation scheme according to an embodiment of the present application;
FIG. 2 is a schematic flow chart of a method for generating a virtual simulation system based on a refrigeration system according to an embodiment of the present application;
FIG. 3 is a flow chart of a method for generating a virtual simulation system based on a refrigeration system according to another embodiment of the present application;
FIG. 4a is a schematic diagram illustrating interaction between a call container interaction interface and a virtual simulation system according to an embodiment of the present application;
FIG. 4b is a schematic diagram of creating a target container provided by an embodiment of the present application;
FIG. 4c is a schematic diagram of an AI energy saving algorithm optimized by a virtual simulation system according to an embodiment of the application;
FIG. 5 is a schematic diagram of a virtual simulation system generating device based on a refrigeration system according to an embodiment of the present application;
fig. 6 is a schematic structural diagram of a computer device according to an embodiment of the present application.
Detailed Description
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application.
In an embodiment of the present application, a refrigeration system refers to a system in which heat is removed from an object or space by a refrigeration device to reduce the temperature of the corresponding object or space. The system can be commonly used in places needing to keep a low-temperature environment, such as a data center machine room, an office building and the like; for ease of illustration, a refrigeration system in a data center will be described hereinafter. The energy efficiency of the data center may be measured by the index PUE (Power Usage Effectiveness), i.e., PUE is an index for evaluating the energy efficiency of the data center, which is equal to a ratio between total energy consumed by the data center (i.e., total energy consumption) and energy consumed by the equipment (IT equipment) load of the data center (i.e., IT equipment energy consumption), i.e., pue=total energy consumption of the data center/IT equipment energy consumption. The total energy consumption of the data center comprises the energy consumption of IT equipment, the energy consumption of a refrigerating system, a power distribution system and the like; IT can be seen that a value of the PUE is greater than 1, and that the closer the value of the PUE is to 1, the less power is consumed by the non-IT devices, thus indicating a better energy efficiency level for the data center.
See fig. 1 a: key refrigeration equipment in a refrigeration system may include, but is not limited to: a chiller (or refrigeration unit, which includes mainly a chiller, condenser, evaporator, etc.), a cooling water pump, a chilled water pump, a cooling tower, a cold storage tank, etc. The core of the refrigerating system is a water chilling unit, which absorbs heat through circulating refrigerant and then discharges the heat, thereby achieving the effect of cooling. It should be noted that fig. 1a only represents the system architecture of the refrigeration system by way of example, and is not limited thereto, for example, the key refrigeration equipment in the refrigeration system may also include a plate heat exchanger and the like; the actual architecture of the refrigeration system can be changed according to the service requirement, and a plurality of factors such as the required refrigeration capacity, the environment temperature, the efficiency of the water chiller, maintenance and the like need to be considered in the design and the use of the actual refrigeration system. Meanwhile, the efficiency and energy conservation of the refrigeration system are also important concerns of the refrigeration industry. In order to increase the efficiency of the refrigeration system and reduce the energy consumption of the refrigeration system, some new technologies and materials are also applied in the design and manufacture of the refrigeration system, such as renewable energy sources, efficient refrigerants, intelligent control, etc.
Aiming at the refrigerating system, the embodiment of the application provides a virtual simulation system generation scheme based on a simulation engine, so as to automatically construct a more accurate virtual simulation system (or referred to as a virtual simulation platform). Referring to FIG. 1b, the virtual simulation system generation scheme may generally include the steps of: and step 1, collecting design data of each refrigeration device in the refrigeration system. And 2, performing simulation modeling on the corresponding refrigeration equipment by using a simulation engine according to the design data of the refrigeration equipment to obtain a preliminary system model corresponding to the refrigeration system, wherein the preliminary system model comprises an initial equipment model corresponding to the refrigeration equipment. And 3, performing identification calibration on model parameters of the primary system model by using a simulation engine according to the operation data of the refrigerating system to obtain a final system model (namely a virtual simulation system corresponding to the refrigerating system). Wherein the operational data of the refrigeration system includes operational data historically generated by each refrigeration device; accordingly, when step 3 is performed, the upstream and downstream boundary conditions of the initial equipment model corresponding to each refrigeration equipment may be obtained, where the upstream and downstream boundary conditions refer to: and (3) ensuring the condition that the initial equipment model can normally run, identifying and calibrating model parameters of the corresponding initial equipment model based on running data generated by histories of the refrigeration equipment and upstream and downstream boundary conditions of the corresponding initial equipment model respectively to obtain target equipment models corresponding to the refrigeration equipment, and connecting the target equipment models corresponding to the refrigeration equipment to obtain a final system model (i.e. a virtual simulation system). Optionally, after the final system model (i.e. the virtual simulation system) is obtained in step 3, the final system model (i.e. the virtual simulation system) may be further containerized and packaged in a standardized manner in step 4 to obtain a standardized interface, so that a user may use the final system model (i.e. the virtual simulation system) to debug and optimize the AI energy-saving algorithm through the standardized interface.
Therefore, when the virtual simulation system corresponding to the refrigeration system is developed by using the virtual simulation system generation scheme provided by the embodiment of the application, the method mainly comprises the steps of simulation modeling, identification and calibration of model parameters, standardized interface encapsulation and the like; the standardized development flow can ensure the universality and consistency of virtual simulation systems developed based on refrigeration systems of different data centers, so that a user can test corresponding AI energy-saving algorithms on different virtual simulation systems through a set of same interaction methods. In addition, by utilizing a simulation engine to simulate modeling and carrying out identification calibration on model parameters based on actual operation data, a refrigerating system based on a two-dimensional drawing or building information model (Building Information Mdeling, BIM) can be converted into a virtual simulation system, and model parameters of each target equipment model in the virtual simulation system are obtained by carrying out parameter identification calibration based on the actual operation data of corresponding refrigerating equipment.
In a specific implementation, the above mentioned virtual simulation system generation scheme may be executed by a computer device, which may be a terminal or a server, i.e. the above mentioned virtual simulation system generation scheme may be executed by a terminal or a server. Alternatively, the virtual simulation system generation scheme mentioned above may be performed by the terminal and the server together. For example, the terminal may be responsible for executing step 1-2 to obtain a preliminary system model corresponding to the refrigeration system, and send the preliminary system model to the server, and the server executes the subsequent step 3-4 based on the preliminary system model; or the server performs identification and calibration of model parameters on the preliminary system model through the step 3 to obtain a virtual simulation system corresponding to the refrigeration system, the virtual simulation system is returned to the terminal, and the terminal performs containerization and standardized encapsulation on the virtual simulation system through the step 4. For another example, the server may be responsible for executing the steps 1-3 to obtain a virtual simulation system corresponding to the refrigeration system, and issue the virtual simulation system to the terminal, and the terminal performs the containerization and standardized encapsulation on the virtual simulation system through the step 4.
The above-mentioned terminals may be smart phones, computers (such as tablet computers, notebook computers, desktop computers, etc.), smart wearable devices (such as smart watches, smart glasses), smart voice interaction devices, smart home appliances (such as smart televisions), vehicle-mounted terminals, aircraft, etc.; the servers mentioned above may be independent physical servers, may be a server cluster or a distributed system formed by a plurality of physical servers, and may also be cloud servers that provide cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDNs (Content Delivery Network, content delivery networks), and basic cloud computing services such as big data and artificial intelligence platforms, and so on. Further, the terminal and the server may be located within or outside the blockchain network, which is not limited; furthermore, the terminal and the server can upload any data stored in the terminal and the server to the blockchain network for storage, so that the data stored in the terminal and the server are prevented from being tampered, and the data security is improved.
Based on the related description of the virtual simulation system generation scheme, the embodiment of the application provides a virtual simulation system generation method based on a refrigeration system. The virtual simulation system generating method based on the refrigeration system can be executed by computer equipment (a terminal or a server), and can also be executed by the terminal and the server together, and the method is not limited to the method; for convenience of explanation, the method for generating the virtual simulation system based on the refrigeration system is described by taking a computer device as an example. Referring to fig. 2, the method for generating a virtual simulation system based on a refrigeration system may include the following steps S201 to S204:
S201, performing simulation modeling on each refrigeration device in the refrigeration system to obtain an initial device model corresponding to each refrigeration device.
In a specific implementation, the computer device can call the simulation engine to perform simulation modeling on each refrigeration device in the refrigeration system to obtain an initial device model corresponding to each refrigeration device, wherein one refrigeration device corresponds to one initial device model. The simulation engine mentioned herein refers to an engine with simulation modeling capability, which can be selected according to actual requirements. For example, the simulation engine may be a model, a type of equation-based, object-oriented programming language that is known as a "new generation building energy system simulation language"; the Modelica adopts a method of symbol programming (symbolic programming), a Modelica compiler can automatically discretize an equation input by a user based on symbol programming and execute numerical solution, and the characteristics of automatic differentiation (automatic differentiation) enable a Modelica model (namely an initial equipment model obtained by using Modelica modeling) to be directly butted with an optimization solution algorithm based on gradient, so that the optimizing speed is increased; in addition, modelica has an active community and interdisciplinary device library as an open source programming language for reference and use by developers. As another example, the simulation engine may be an energy plus (a building energy consumption simulation engine), TRNSYS (TransientSystem Simulation Program, i.e., transient system simulator), or other engine. For ease of description, the simulation engine will be described as Modelica.
Any initial device model may include information such as model parameters and model interfaces. Further, the model parameters referred to herein may be determined based on empirical values or by consulting related data such as Modelica Buildings Library (open source software library for modeling and simulation of building systems) user help documents on the official network. The model interfaces referred to herein may include: a model input interface, a model output interface, a fluid inlet interface, a fluid outlet interface, and so forth; the input data corresponding to the model input interface and the output data of the model output interface can be determined according to service requirements, and the inflow data corresponding to the fluid inlet interface and the outflow data corresponding to the fluid outlet interface can be determined according to physical information of upstream fluid and downstream fluid of the corresponding refrigeration equipment. The physical information of the fluid upstream and downstream of the refrigeration equipment includes: physical information of fluid upstream of the refrigeration equipment (i.e., fluid flowing into the refrigeration equipment) and physical information of fluid downstream of the refrigeration equipment (i.e., fluid flowing out of the refrigeration equipment); the physical information of the upstream fluid is used for determining inflow data corresponding to the fluid inlet interface, and the physical information of the downstream fluid of the refrigeration equipment is used for determining outflow data corresponding to the fluid outlet interface. While the physical information of either fluid (upstream fluid, downstream fluid) may include: temperature, flow, composition, pressure, etc. of the corresponding fluid. It should be noted that the fluid mentioned in the embodiments of the present application refers to a flowable object, for example, the fluid may be water; and the chiller has two loops, a cooling side and a freezing side, the water of the cooling side loop may be referred to as cooling water and the water of the freezing side loop may be referred to as chilled water.
For example, for a chiller in a refrigeration system, its corresponding initial equipment model may be referred to as a chiller model. In the chiller model, the performance of the chiller can be represented by the following model mathematical formulas 1.1-1.4:
CAPFT＝a 1 +T chw,out (a 2 +a 3 T chw,out )+T cw,out (a 4 +a 5 T cw,out )+a 6 T chw,out T cw,out 1.1
EIRFT＝b 1 +T chw,out (b 2 +b 3 T chw,out )+T cw,out (b 4 +b 5 T cw,out )+b 6 T chw,out T cw,out 1.2
EIRFPLR＝c 1 +T cw,out (c 2 +c 3 T cw,out )+PLR(c 4 +c 5 PLR+c 6 PLR 2 )+c 7 T cw,out PLR 1.3
P chiller ＝P ref CAPFT EIRFT EIRFPLR 1.4
Each of the model mathematical formulas 1.1 to 1.4 may correspond to a performance curve. The model math equation 1.1 shows the available cooling Capacity (CAPFT) of the chiller as a function of the temperature (T) of the fluid leaving the condenser (Tcw) cw，out ) And leave the evaporator (T) chw，out ) Is a function of the fluid temperature of the model mathematical formula 1.1, a 1 -a 6 Are all coefficients; the model math equation 1.2 shows the full load Efficiency (EIRFT) of the chiller as a function of the temperature of the fluid leaving the condenser and the temperature of the fluid leaving the evaporator, b in the model math equation 1.2 1 -b 6 Are all coefficients; model math equation 1.3 shows the chiller Efficiency (EIRFPLR) as a function of the fluid temperature leaving the condenser and Part Load Ratio (PLR), c in model math equation 1.3 1 -c 6 Are all coefficients; the model mathematical formula 1.4 represents the actual power (P chiller ) Is based on rated power (P ref ) Is a relation of (3).
When using the chiller model, it is necessary to specify the fluid working media on the cooling side and the freezing side: medium1 (fluid working Medium on the cooling side) and Medium2 (fluid working Medium on the freezing side), and three performance curves (performance curves corresponding to the CAPFT, EIRFT and EIRFPLR, respectively) of the chiller are required to be identified based on the operation data generated by the chiller history or the manufacturer data, and Nominal (Nominal) operation data for limiting the operation parameters of the refrigeration equipment is required to be specified based on the manufacturer data. For example, nominal operating condition data for a chiller may include: nominal refrigeration capacity, nominal COP (energy efficiency ratio), nominal flow, nominal evaporator inlet and outlet temperatures, and nominal condenser inlet and outlet temperatures, etc. Based on this, the model parameters of the chiller model may include at least: three performance curves of the Medium1, the Medium2 and the cold machine, and nominal working condition data of the cold machine.
Additionally, an overview of the model interfaces for the chiller model can be found in Table 1 below:
TABLE 1
In table 1, input and Output in the interface type column refer to the Input and Output required by the chiller model, respectively; the interface name column specifies the names of the model interfaces (i.e., model input interface, model output interface, fluid inlet interface, and fluid outlet interface); the interface description column contains a textual description of the respective model interface to aid in understanding the model. Meanwhile, the data types corresponding to the input and output contained in the interface type column are provided for reference, and may be any of the following: real (Real type), boolean (Boolean type), intel (Integer type). Based on the above table 1, the model input interface of the chiller model may include: an interface (on) for inputting the operating state of the compressor, and an interface (TSet) for inputting the chilled water outlet temperature setpoint; the model output interface of the chiller model may include: an interface (pchller) for outputting compressor power. That is, the chiller model inputs the operating state of the compressor and the chilled water outlet temperature setpoint, and outputs the compressor power.
As another example, for a refrigeration device, a plate heat exchanger in a refrigeration system, its corresponding initial device model may be referred to as a heat exchanger model. If there is an outlet temperature control demand, the heat exchanger model may be a model with outlet temperature PID (automatic controller) control; the heat exchanger model can realize PID control of the outlet chilled water temperature, and when the PID control is started, the control of the chilled water side temperature can be realized by adjusting the flow of the three-way valve inside the heat exchanger model. In the heat exchanger model, the performance calculation of the plate heat exchanger is based on the heat transfer unit Number (NTU) method, which can be expressed specifically by the following model mathematical formulas 1.5 to 1.7:
In the above model mathematical formulas 1.5-1.7, NTU represents the number of heat transfer units, UA represents the total heat transfer coefficient, RC represents the small amount of water on both sidesThe patients with large dosage>The ratio between epsilon indicates the efficiency of the plate heat exchanger.
When the heat exchanger model is used, fluid working media on a cooling side and a freezing side need to be specified: medium1 (fluid Medium on the cooling side) and Medium2 (fluid Medium on the freezing side), and the type (Heat Exchanger Configuration) of plate heat exchanger, which may be concurrent, countercurrent, mixed flow, etc.; in addition, parameters of the plate heat exchanger under the nominal working condition, such as flow, heat exchanger efficiency and the like, are specified based on manufacturer data. Based on this, the model parameters of the heat exchanger model may include at least: medium1, medium2, type of plate heat exchanger, and a number of parameters of the plate heat exchanger under nominal operating conditions.
Additionally, an overview of the model interfaces for the heat exchanger model can be found in table 2 below:
TABLE 2
As another example, for a refrigeration plant, a cooling tower in a refrigeration system, its corresponding initial plant model may be referred to as a cooling tower model. In the cooling tower model, the performance of the cooling tower can be calculated by the following model math
The formula 1.8-1.9:
P a ＝f 1 +f 2 Q a +f 3 Q a 2 1.9
Each of the model math formulas 1.8-1.9 may correspond to a performance curve, T in the model math formula 1.8 app Indicating the approach temperature, T wb Represents the outdoor wet bulb temperature (i.e. the air wet bulb temperature outside the tower), T ran The temperature difference of the inlet water and the outlet water of the cooling water is represented, and r represents the liquid-gas ratio of the cooling tower; p in model math equation 1.9 a Represents the power of a fan in the cooling tower, Q a Represents the flow rate of the fan, f 1 -f 3 Are coefficients. It can be seen that the performance represented by the model mathematical formulas 1.8-1.9 includes not only the close temperature relationship of the cooling tower, but also the performance of the fan inside the cooling tower.
When the cooling tower model is used, a working Medium (Medium 3) inside the cooling tower and a heat transfer form (Vol) inside the cooling tower need to be specified, a flow-power performance curve (namely a performance curve between flow and power, specifically, a performance curve corresponding to a model mathematical formula 1.9) of a fan inside the cooling tower needs to be specified based on operation data or manufacturer data generated by the history of the cooling tower, and a plurality of parameters of the cooling tower under nominal working conditions such as a near temperature, a temperature difference of inlet and outlet of cooling water, a flow of the fan, a liquid-gas ratio, an outside air wet bulb temperature and the like need to be specified based on the manufacturer data. Based on this, the model parameters of the cooling tower model may include at least: medium3, flow-to-power performance curves of fans, and various parameters of the cooling tower at nominal operating conditions.
Additionally, an overview of the model interfaces for the cooling tower model can be found in Table 3 below:
TABLE 3 Table 3
In table 3 above, input and Output in the interface type column refer to the inputs and outputs required for the cooling tower model, respectively; the interface name column specifies the names of the model interfaces (i.e., model input interface, model output interface, fluid inlet interface, and fluid outlet interface); the interface description column contains a textual description of the respective model interface to aid in understanding the model. Meanwhile, the data types corresponding to the input and output contained in the interface type column are provided for reference, and may be any of the following: real, boost, intelger. Based on the above table 3, the model input interface of the cooling tower model may include: an interface (TAir) for inputting a wet bulb temperature of the incoming air, and an interface (y) for inputting a fan control signal; the model output interface of the cooling tower model may include: an interface (PFan) for outputting fan power, and an interface (TLvg) for outputting tower cooling water temperature. That is, the cooling tower model inputs a fan control signal and an outdoor wet bulb temperature, which outputs the power of the internal fan and the tower outlet cooling water temperature.
As another example, for a refrigeration plant that is a cooling/chilled water pump (i.e., a cooling water pump or a chilled water pump) in a refrigeration system, its corresponding initial plant model may be referred to as a cooling/chilled water pump model (i.e., a cooling water pump model or a chilled water pump model). In the cooling/freezing water pump model, the characteristics of the cooling/freezing water pump can be represented by the following model mathematical formulas 2.0 to 2.1:
H＝e 1 +e 2 Q b +e 3 Q b 2 2.0
P b ＝E 1 +E 2 Q b +E 3 Q b 2 2.1
Each of the model mathematical formulas 2.0-2.1 may correspond to a performance curve. H in the model mathematical formula 2.0 represents the lift, Q of the cooling/freezing water pump b Indicating the flow rate of the cooling/freezing water pump e 1 -e 3 Is a coefficient; p in model math equation 2.1 b Indicating the work of the cooling/freezing water pumpRate, E 1 -E 3 Is a coefficient. It can be seen that the characteristics of the cooling/freezing water pump represented by the model mathematical formulas 2.0-2.1 include not only the flow-head characteristics of the cooling/freezing water pump (i.e., the characteristics between the flow and the head of the cooling/freezing water pump) but also the flow-power characteristics of the cooling/freezing water pump (i.e., the characteristics between the flow and the power of the cooling/freezing water pump).
When using the cooling/freezing water pump model, a working Medium (Medium 4) transported by the cooling/freezing water pump needs to be specified, 2 performance curves (namely, a flow-lift performance curve corresponding to a model mathematical formula 2.0 and a flow-power performance curve corresponding to a model mathematical formula 2.1) of the cooling/freezing water pump need to be specified based on operation data or manufacturer data generated by the history of the cooling/freezing water pump, and a control input form (control input type) of the cooling/freezing water pump needs to be specified, wherein the control input form can be stage, constant or continuous. Based on this, the model parameters of the cooling/chilled water pump model may include at least: medium4, 2 performance curves of the cooling/chilled water pump, and control input form of the cooling/chilled water pump.
Additionally, an overview of the model interfaces for the cooling/chilled water pump model can be found in Table 4 below:
TABLE 4 Table 4
In table 4 above, input and Output in the interface type column refer to the inputs and outputs required for the cooling/chilled water pump model, respectively; the interface name column specifies the names of the model interfaces (i.e., model input interface, model output interface, fluid inlet interface, and fluid outlet interface); the interface description column contains a textual description of the respective model interface to aid in understanding the model. Meanwhile, the data types corresponding to the input and output contained in the interface type column are provided for reference, and may be any of the following: real, boost, intelger. Based on the above table 3, the model input interface of the cooling/chilled water pump model may include: an interface (Nrpm) for inputting the rotational speed of the water pump, and an interface (Stage) for inputting the pressure head input signal of the water pump, the interface (Stage) being an optional interface; the model output interface of the cooling/chilled water pump model may include: an interface (Ppump) for outputting the pump power, and an interface (y _ actual) for outputting the actual normalized pump speed. That is, the cooling/chilled water pump model may input a water pump speed, which may output water pump power.
S202, respectively acquiring the upstream and downstream boundary conditions of each initial equipment model, wherein the upstream and downstream boundary conditions of any initial equipment model are determined according to the physical information of upstream and downstream fluids of corresponding refrigeration equipment.
In the actual operation process of the refrigerating system, for the ith refrigerating device in the refrigerating system, fluid processed by the refrigerating device positioned at the upstream of the ith refrigerating device can flow into the ith refrigerating device, after the ith refrigerating device processes the corresponding fluid according to the physical information of the flowing fluid, the processed fluid can be transmitted to the refrigerating device positioned at the downstream of the ith refrigerating device for processing, and so on. Wherein I is [1, I ], I is the number of refrigeration devices in the refrigeration system. It follows that physical information of the upstream fluid (i.e., fluid flowing into the refrigeration appliance) and the downstream fluid (i.e., fluid flowing into the refrigeration appliance) of any refrigeration appliance can affect the operation of the respective refrigeration appliance.
Based on this, the study further showed that: an initial equipment model obtained by carrying out simulation modeling on any refrigeration equipment also needs to run depending on physical information of upstream and downstream fluid of the corresponding refrigeration equipment. Therefore, the upstream and downstream boundary conditions of the corresponding initial equipment model can be determined according to the physical information of the upstream and downstream fluid of each refrigeration equipment; the upstream and downstream boundary conditions of any initial equipment model include: information required for running the corresponding initial equipment model, such as physical information of the upstream and downstream fluids, or information obtained by further optimizing the physical information of the upstream and downstream fluids, and the like. Wherein the physical information of the fluid upstream and downstream of the refrigeration device comprises: physical information of fluid upstream of the refrigeration equipment and physical information of fluid downstream of the refrigeration equipment; and the physical information of either fluid (upstream fluid, downstream fluid) may include: temperature, flow, composition, pressure, etc. of the corresponding fluid.
And S203, identifying and calibrating model parameters of the corresponding initial equipment model based on operation data generated by histories of the refrigeration equipment and upstream and downstream boundary conditions of the corresponding initial equipment model respectively to obtain a target equipment model corresponding to the refrigeration equipment.
The model parameters of the model are correctly identified and calibrated, so that the model is a precondition for ensuring reasonable operation; therefore, after the computer equipment is modeled to obtain the initial equipment model corresponding to each refrigeration equipment, the model parameters of the corresponding initial equipment model can be identified and calibrated based on the operation data generated by the history of each refrigeration equipment and the upstream and downstream boundary conditions of the corresponding initial equipment model respectively to obtain the target equipment model corresponding to each refrigeration equipment, and the target equipment model corresponding to any refrigeration equipment is an equipment model which can reasonably operate.
In a specific implementation, when executing step S203, the computer device may construct, according to each initial device model and upstream and downstream boundary conditions of the corresponding initial device model, a device-level verification model corresponding to each initial device model and using operation data generated by field history as a boundary condition, where the device-level verification model corresponding to any initial device model includes: the respective initial device model and upstream and downstream boundary conditions of the respective initial device model, and any one of the initial device models operates with operation of the device-level verification model. And then, the computer equipment controls the equipment-level verification models corresponding to the corresponding initial equipment models to operate based on operation data generated by the refrigerating equipment histories corresponding to the initial equipment models respectively, so that the model parameters of the corresponding initial equipment models are identified and calibrated according to the operation results of the equipment-level verification models, and the target equipment models corresponding to the refrigerating equipment are obtained.
That is, for the ith refrigeration equipment, the computer equipment may take the initial equipment model corresponding to the ith refrigeration equipment as the ith initial equipment model, and construct the equipment level verification model corresponding to the ith initial equipment model according to the ith initial equipment model and the upstream and downstream boundary conditions of the ith initial equipment model. The device-level verification model comprises an ith initial device model and upstream and downstream boundary conditions of the ith initial device model; and the constructed equipment-level verification model takes the operation data generated by the field history of the ith refrigeration equipment as boundary conditions, namely, the model input data of the constructed equipment-level verification model is determined according to the operation data generated by the field history of the ith refrigeration equipment. Based on the method, the operation of the constructed equipment level verification model can be controlled according to the operation data generated by the history of the ith refrigeration equipment, so that the model parameters of the ith initial equipment model are identified and calibrated according to the operation result of the constructed equipment level verification model, and the target equipment model corresponding to the ith refrigeration equipment is obtained.
And S204, connecting the target equipment models corresponding to the refrigeration equipment according to the equipment configuration information of the refrigeration system to obtain a virtual simulation system corresponding to the refrigeration system.
In a specific implementation, the computer device may obtain device configuration information of the refrigeration system, where the device configuration information is used to indicate a connection relationship between each refrigeration device in the refrigeration system; the embodiment of the application is not limited to the specific form of the equipment configuration information, for example, the equipment configuration information may be a two-dimensional drawing for describing the instruction equipment, or the equipment configuration information may be a table containing the connection relationship between the refrigeration equipment, or the like. After the equipment configuration information is obtained, the computer equipment can connect the target equipment models corresponding to the refrigeration equipment according to the connection relation among the refrigeration equipment indicated by the equipment configuration information, so as to obtain the virtual simulation system corresponding to the refrigeration system. That is, after identifying and calibrating the model parameters of each initial equipment model to obtain the target equipment models corresponding to the refrigeration equipment, connecting the target equipment models according to the equipment configuration diagram of the actual case, so as to obtain the virtual simulation system corresponding to the refrigeration system; and after the input of the virtual simulation system is reasonably specified according to the historical operation data, the virtual simulation system can be operated.
According to the embodiment of the application, simulation modeling can be carried out on each refrigeration device in the refrigeration system to obtain the initial device model corresponding to each refrigeration device, physical information of upstream and downstream fluid of each refrigeration device is respectively obtained, the determined upstream and downstream boundary conditions of the corresponding initial device model are used for ensuring that each initial device model can normally operate based on the obtained upstream and downstream boundary conditions, so that model parameters of the corresponding initial device model can be identified and calibrated based on operation data generated by histories of each refrigeration device and the upstream and downstream boundary conditions of the corresponding initial device model respectively to obtain the target device model corresponding to each refrigeration device, the operation state of the corresponding refrigeration device can be accurately reflected by each target device model, the self-adaptive characteristic is realized, and a relatively accurate virtual simulation system can be automatically generated by connecting each target device.
Based on the related description of the method embodiment shown in fig. 2, the embodiment of the application further provides a virtual simulation system generation method based on a refrigeration system; in the embodiment of the application, the method for generating the virtual simulation system based on the refrigerating system by the computer equipment is still taken as an example for explanation. Referring to fig. 3, the method for generating a virtual simulation system based on a refrigeration system may include the following steps S301 to S306:
S301, performing simulation modeling on each refrigeration device in the refrigeration system to obtain an initial device model corresponding to each refrigeration device, wherein one refrigeration device corresponds to one initial device model.
In a specific implementation, taking a refrigeration system including a cooling tower, a water chiller, a plate heat exchanger and a freezing/cooling water pump as an example, the general idea of performing simulation modeling on each refrigeration device in the refrigeration system can include the following two parts:
design data and operation data collection:
specifically, manual information of each refrigeration device in the field is collected as much as possible, design data of the corresponding refrigeration device is obtained based on the manual information of each refrigeration device, and the design data of any refrigeration device comprises at least one design parameter. For example, design data for a cooling tower may include the following design parameters: design working condition data such as design power, design temperature, design flow and the like; the design data of the water chiller can comprise the following design parameters: nominal working condition data such as design flow, design inlet and outlet temperature of the evaporator and design COP (coefficient of performance) design value of the condenser; the design data of the plate heat exchanger may include the following design parameters: design working condition data such as design flow, design heat exchange area, heat exchange coefficient and the like; the design data of the cooling/freezing water pump can comprise the following design parameters: power curve, hydraulic characteristic curve, etc.
In addition, as for design parameters which cannot be obtained by manual information due to loss of manual information or degradation of equipment performance, it is possible to consider that the estimation is made by using the operation data of the corresponding refrigeration equipment measured when the refrigeration system is operated. The operational data employed may be obtained in direct or indirect form as corresponding design parameters, such as: the relevant design parameters may be read directly from fields in the operating data or equivalent scaling of certain variables may be performed using existing data. Taking a cooling water pump as an example, for a power curve, the flow-power data under a specific working condition can be read from the operation data to obtain the power curve; for the design parameter of the hydraulic characteristic curve, the flow-lift data of the cooling water pump under a specific working condition can be read from the operation data of the cooling water pump, so that the hydraulic characteristic curve is obtained according to the read flow-lift data. If the cooling water pump does not directly monitor the lift, i.e. the running data does not include the lift data, the calculation of the pressure rise can be performed through the pressure monitoring points before and after the cooling water pump, so that the calculation result is equivalent to replace the required lift data.
It should be noted that, the collected operation data should be comprehensive, so as to cover the seasons (i.e. outdoor temperatures) as much as possible, and cover the possible operation conditions of the refrigeration equipment (e.g. independent/combined use of free cold source and water chiller, etc.) as much as possible.
And (II) modeling:
specifically, for any refrigeration equipment, according to the existing design data and operation data range or actual simulation modeling requirement, selecting which candidate equipment model in Modelica Buildings Library (model library) is used, determining model parameters required by the selected candidate equipment model based on the design data and operation data corresponding to the refrigeration equipment, and embedding the determined model parameters into the selected candidate equipment model to obtain the corresponding initial equipment model.
Taking the cooling water pump as an example, in Modelica Buildings Library, there are 4 different candidate cooling water pump models (i.e., candidate equipment models) in total, which are classified according to different input control amounts: the method comprises the following steps of taking lift data as a candidate cooling water pump model of an input quantity, taking mass flow as the candidate cooling water pump model of the input quantity, taking rotating speed as the candidate cooling water pump model of the input quantity, and taking normalized rotating speed as the candidate cooling water pump model of the input quantity. For the design parameters in the collected design data of the cooling water pump and the operation data generated by the history of the cooling water pump, candidate cooling water pump models meeting the specific case requirement (simulation requirement) can be selected from the 4 different candidate cooling water pump models. Taking a specific case requirement as an example to simulate and obtain a variable-frequency cooling water pump model, according to the running data of the cooling water pump, selecting a candidate cooling water pump model with the rotating speed or the normalized rotating speed as an input quantity from the 4 candidate cooling water pump models.
Then, model parameters such as a flow-power characteristic curve, a flow-lift characteristic curve and the like of the cooling water pump can be input into the selected candidate cooling water pump models to obtain an initial cooling water pump model (namely an initial equipment model) corresponding to the cooling water pump. The input model parameters can be obtained through design data of the cooling water pump or field historical operation data (namely, operation data generated in field history) of the cooling water pump. For cases where the equipment has long operation years and the use of manufacturer data is insufficient to reflect the current real operation conditions, the model parameters required by the selected cooling water pump model are recommended to be obtained by screening the on-site historical operation data. That is, the manufacturer manual may be consulted to obtain design data, and the related data of the flow-power characteristic curve and the flow-lift characteristic curve may be found from the design data and input into the characteristic curve module of the candidate cooling water pump model to obtain the initial cooling water pump model. If the manufacturer data is not available or the performance change of the equipment after a few years of operation is considered, the flow-power characteristic curve and the flow-lift characteristic curve under specific working frequency can be extracted from the field historical operation data and input into the characteristic curve module to obtain an initial cooling water pump model.
It can be understood that: if the field history operation data in the specific case is insufficient to obtain the model parameters (such as characteristic curves) required by the selected cooling water pump model, the relevant model parameters can be obtained by adopting the design data from the factory of the manufacturer. In addition, under the condition that the design data and the field history operation data can provide the model parameters required by the selected cooling water pump model, the model parameters in the design data can be reversely calibrated according to the field history operation data, so that the output of the initial equipment model is as close to the field actual measurement data as possible, and the real operation condition of the refrigerating system is reflected.
According to the same thought, selecting a candidate chilled water pump model, a candidate cooling tower model, a candidate chiller model, a candidate heat exchanger model and the like which are matched with the case from Modelica Buildings Library according to the need; and respectively determining model parameters required by each selected model, and inputting the determined model parameters into the corresponding models to obtain the initial equipment model.
Based on the above-mentioned general idea of performing simulation modeling on each refrigeration device, when the computer device executes step S301, a plurality of candidate device models corresponding to the ith refrigeration device in the refrigeration system may be obtained, and specifically, each candidate device model may be obtained from a model library, where each candidate device model is obtained by performing simulation modeling on the ith refrigeration device, and different candidate device models correspond to different model input data (i.e. model input amounts). Then, selecting one candidate equipment model from a plurality of candidate equipment models according to the model input data indicated by the simulation requirements; the model parameters of the selected candidate equipment model are obtained, and the obtained model parameters are determined based on at least one of design data of the ith refrigeration equipment and operation data generated by the history of the ith refrigeration equipment; and embedding the acquired model parameters into the selected candidate equipment models to obtain an initial equipment model corresponding to the ith refrigeration equipment. Wherein, I is the number of refrigeration equipment in the refrigeration system; the simulation requirements referred to herein may be set according to actual requirements, which may indicate model input data, e.g., the simulation requirements are simulation of a variable frequency water pump model, where the simulation requirements refer to model input data being rotational speed or normalized rotational speed.
Further, the mode of determining the model parameters of the selected candidate equipment model based on at least one of the design data of the ith refrigeration equipment and the operation data generated by the history of the ith refrigeration equipment may be any one of the following modes:
embodiment one: model parameters of the selected candidate device model may be determined based on the design data, and if determining the model parameters based on the design data fails, determining the model parameters of the selected candidate device model based on the operational data.
Embodiment two: model parameters of the selected candidate device model may be determined based on the operational data, and if the determination of the model parameters based on the operational data fails, the model parameters of the selected candidate device model are determined based on the design data.
Embodiment III: whether to use the design data or the operational data may be determined based on the operational duration of the ith refrigeration equipment to determine the model parameters. That is, the operation time length of the ith refrigeration equipment can be obtained; if the running time length is greater than or equal to the time length threshold, the running data can be considered to reflect the condition of the ith refrigeration equipment more accurately than the design data, so that the model parameters of the selected candidate equipment model can be determined based on the running data generated by the history of the ith refrigeration equipment at the moment so as to improve the accuracy of the model parameters; if the operation time length is smaller than the time length threshold value, the design parameters are considered to reflect the situation of the ith refrigeration equipment more accurately than the operation data, so that the model parameters of the selected candidate equipment models can be determined based on the design data of the ith refrigeration equipment at the moment, and the accuracy of the model parameters is improved.
Embodiment four: the design working condition of the ith refrigeration equipment (namely, the working condition indicated by the design data of the ith refrigeration equipment) and the operation working condition of the ith refrigeration equipment (namely, the working condition indicated by the operation data generated by the history of the ith refrigeration equipment) can be judged to be consistent, so that under the condition that the two operation working conditions are inconsistent, the model parameters are determined by adopting the design data, the accuracy of the model parameters is ensured, under the condition that the two operation working conditions are consistent, when the difference between the design data and the operation data is large, the model parameters are determined by adopting the operation data, so that the model parameters can be more consistent with the actual operation conditions, and when the difference between the design data and the operation data is small, the model parameters are determined by adopting the design data. That is, the computer device may perform a consistency check on the design operating condition of the ith refrigeration equipment and the operating condition of the ith refrigeration equipment; if the design working condition and the operation working condition do not pass the consistency check, determining model parameters of the selected candidate equipment model based on the operation data; and if the design working condition and the operation working condition pass the consistency check, acquiring the difference degree between the design data and the operation data, screening effective data from the design data and the operation data according to the acquired difference degree, and determining the model parameters of the selected candidate equipment model based on the effective data. Specifically, if the acquired difference is greater than or equal to a difference threshold, selecting operation data from design data and the operation data as effective data; and if the acquired difference is smaller than the difference threshold, selecting design data from the design data and the operation data as effective data.
S302, respectively acquiring the upstream and downstream boundary conditions of each initial equipment model, wherein the upstream and downstream boundary conditions of any initial equipment model are determined according to the physical information of upstream and downstream fluids of corresponding refrigeration equipment; wherein the upstream and downstream boundary conditions of the initial equipment model include: information required to run the corresponding initial device model.
S303, identifying and calibrating model parameters of the corresponding initial equipment model based on operation data generated by histories of the refrigeration equipment and upstream and downstream boundary conditions of the corresponding initial equipment model respectively to obtain a target equipment model corresponding to the refrigeration equipment.
In a specific implementation of step S303, the computer device may perform identification calibration on model parameters of an initial device model corresponding to each refrigeration device in the refrigeration system, so as to obtain a target device model corresponding to each refrigeration device. Wherein, for the ith refrigeration equipment in the refrigeration system, the following steps s11-s15 can be performed:
and s11, taking the initial equipment model corresponding to the ith refrigeration equipment as the ith initial equipment model.
And s12, constructing an equipment level verification model corresponding to the ith initial equipment model by adopting the ith initial equipment model and upstream and downstream boundary conditions of the ith initial equipment model.
Specifically, the upstream and downstream boundary conditions of the ith initial equipment model may be connected to the fluid interface of the ith initial equipment model to generate an equipment-level verification model corresponding to the ith initial equipment model. From the foregoing, the upstream and downstream boundary conditions include physical information of the upstream fluid and physical information of the downstream fluid, and the fluid interface includes a fluid inlet interface and a fluid outlet interface; based on this, the computer device may connect the physical information of the upstream fluid in the upstream and downstream boundary conditions of the i-th initial device model to the fluid inlet interface in the i-th initial device model, i.e., designate the input of the fluid inlet interface in the i-th initial device model as the physical information of the upstream fluid in the upstream and downstream boundary conditions; and connecting the physical information of the downstream fluid in the upstream and downstream boundary conditions to the fluid outlet interface in the ith initial equipment model, namely designating the output of the fluid outlet interface in the ith initial equipment model as the physical information of the downstream fluid in the upstream and downstream boundary conditions, so as to generate a corresponding equipment-level verification model.
It should be noted that this is merely illustrative of one way of how to construct the device-level verification model, and is not exhaustive; in other embodiments, other approaches (e.g., neural network model based approaches) may also be employed to construct the device-level verification model. The device-level verification model constructed in any mode comprises the following steps: an ith initial equipment model and upstream and downstream boundary conditions of the ith initial equipment model; and, the ith initial device model is run with the device level verification model running.
And s13, identifying and calibrating model parameters of the ith initial equipment model according to the equipment-level verification model and operation data generated by the ith refrigeration equipment history to obtain a target equipment model corresponding to the ith refrigeration equipment.
In a specific implementation, the device-level verification model can be controlled to operate according to the operation data generated by the history of the ith refrigeration device, and the model parameters of the ith initial device model are identified and calibrated according to the operation result of the device-level verification model to obtain the target device model corresponding to the ith refrigeration device. Alternatively, the following steps s131-s133 may be performed:
s131, obtaining model input data of the ith initial equipment model from operation data generated by the ith refrigeration equipment history, and obtaining data to be output by the ith initial equipment model under the model input data as model tag data.
Specifically, the ith initial equipment model may include a model input interface, and the computer device may obtain, from the operation data historically generated by the ith refrigeration equipment, data adapted to the model input interface according to the function of the model input interface, to construct model input data of the ith initial equipment model. It can be understood that if the operation data generated by the history of the ith refrigeration equipment does not include the data adapted to the model input interface, the data adapted to the model input interface can be obtained by conversion according to the operation data generated by the history of the ith refrigeration equipment, and the model input data of the ith initial equipment model can be constructed by adopting the converted data. For example, if the ith initial equipment model is a cooling water pump model, the model input interface included in the ith initial equipment model is used for receiving the rotation speed of the cooling water pump, and the rotation speed (i.e. the data matched with the model input interface) can be obtained from the operation data generated by the history of the cooling water pump to construct the model input data of the ith initial equipment model. If the operation data does not include the rotation speed, conversion can be performed based on the motor operation frequency in the operation data, and the model input data of the ith initial equipment model can be constructed by adopting the converted rotation speed.
Similarly, the ith initial equipment model may include a model output interface, and the computer device may obtain, according to the function of the model output interface, a parameter value to be output by the model output interface from the operation data historically generated by the ith refrigeration equipment to construct model tag data of the ith initial equipment model. It can be understood that if the operation data generated by the i-th refrigeration equipment history does not include the parameter value to be output by the model output interface, the parameter value to be output by the model output interface can be obtained by conversion according to the operation data generated by the i-th refrigeration equipment history, and the model label data of the i-th initial equipment model is constructed by adopting the converted parameter value. For example, if the i-th initial equipment model is a cooling water pump model, and the model output interface included in the i-th initial equipment model is used for outputting the power of the cooling water pump, the model label data of the i-th initial equipment model can be constructed by acquiring the power (i.e. the parameter value to be output by the model output interface) from the operation data generated by the history of the cooling water pump. If the operation data does not include power, the power consumption in the operation data can be converted, and the converted power is used for constructing the model tag data of the ith initial equipment model.
It should be noted that, the model tag data mentioned above may include: the model output interface outputs parameter values at a certain time point. Alternatively, the above-mentioned model output data may also include: the model output interface actually outputs the parameter value at each of a plurality of time points, which may be consecutive time points; under the condition, the model tag data comprise more parameter values, the data are rich, and the accuracy of the subsequent identification and calibration of the model parameters based on the model tag data can be effectively improved.
And s132, controlling the equipment-level verification model to operate according to the model input data, and acquiring the data actually output by the ith initial equipment model as model output data in the operation process of the equipment-level verification model.
Specifically, the model input data may be input to the model input interface of the ith initial equipment model in the equipment-level verification model, so that the equipment-level verification model operates according to the model input data, and in the operation process of the equipment-level verification model, the data actually output by the ith initial equipment model is obtained as the model output data.
And s133, identifying and calibrating model parameters of the ith initial equipment model according to the model label data and the model output data to obtain a target equipment model corresponding to the ith refrigeration equipment.
In one embodiment, if the model tag data includes: the model output interface outputs parameter values at a target time point, and the model output data comprises: the model output interface actually outputs the parameter value at the target time point. In this case, the computer device may calculate a data difference between the model tag data and the model output data at step s133, and calibrate model parameters of the ith initial equipment model according to a direction of reducing the data difference, to obtain a target equipment model corresponding to the ith refrigeration equipment.
It should be noted that after the data difference is calculated, the model parameters of the ith initial equipment model may be calibrated directly according to the direction of reducing the data difference, or the size relationship between the data difference and the difference threshold may be detected, if the data difference is greater than or equal to the difference threshold, the step of calibrating the model parameters of the ith initial equipment model according to the direction of reducing the data difference is triggered, if the data difference is less than the difference threshold, the model parameters of the ith initial equipment model may be considered to be more accurate, and at this time, the model parameters of the ith initial equipment model may be kept unchanged, so as to obtain the target equipment model corresponding to the ith refrigeration equipment, that is, the target equipment model is the ith initial equipment model.
Further, when calibrating the model parameters of the ith initial equipment model according to the direction of reducing the data difference, the model parameters of the ith initial equipment model may be updated according to the direction of reducing the data difference, so as to calibrate the corresponding model parameters; or adding a correction coefficient to the model parameter of the ith initial equipment model in the model code of the model parameter of the ith initial equipment model according to the direction of reducing the data difference value so as to calibrate the corresponding model parameter. Wherein, the reference herein to "in a direction of decreasing the data difference" means: parameter calibration direction with minimized data difference as target; the calibration of the model parameters is performed in the direction, so that the data difference value generated by the initial equipment model after each calibration is smaller than the data difference value generated by the initial equipment model before the calibration. For example, the data difference obtained by this calculation is 0.85, and then the data difference generated by calibrating the model parameters after calibrating the model parameters of the initial equipment model according to the direction of reducing the data difference should be less than 0.85.
In another embodiment, if the model tag data includes: the model output interface outputs parameter values at each of a plurality of time points, and the model output data includes: the model output interface actually outputs parameter values at each of a plurality of time points. In this case, the computer device may determine, at step s133, a trend of change in the parameter value corresponding to the model tag data according to each parameter value in the model tag data; and determining the change trend of the parameter value corresponding to the model output data according to each parameter value in the model output data. It should be noted that, the method for determining the parameter value change trend corresponding to any data (i.e., model output data and model label data) in the embodiment of the present application is not limited; for example, the corresponding parameter value change trend can be obtained by performing mathematical analysis on each parameter value in any data, or the corresponding parameter value change trend can be output by learning each parameter value in any data based on a neural network model. After two parameter value change trends (namely, a parameter value change trend corresponding to model tag data and a parameter value change trend corresponding to model output data) are determined, consistency check can be carried out on the determined two parameter value change trends to obtain a consistency check result, and according to the consistency check result, the model parameters of the ith initial equipment model are identified and calibrated to obtain a target equipment model corresponding to the ith refrigeration equipment.
According to the consistency verification result, identifying and calibrating the model parameters of the ith initial equipment model to obtain a specific implementation mode of the target equipment model corresponding to the ith refrigeration equipment, wherein the specific implementation mode comprises the following steps: if the consistency check result indicates that the two parameter value change trends do not have consistency, determining that the model parameters of the ith initial equipment model are abnormal, and carrying out simulation modeling on the ith refrigeration equipment again to obtain a target equipment model corresponding to the ith refrigeration equipment. If the consistency check result indicates that the two parameter value change trends have consistency, the model parameters of the ith initial equipment model can be considered to be more accurate, and the model parameters of the ith initial equipment model can be kept unchanged at the moment, so that a target equipment model corresponding to the ith refrigeration equipment is obtained; or, carrying out data drift detection between the model label data and the model output data, and carrying out identification calibration on the model parameters of the ith initial equipment model according to the data drift detection result to obtain a target equipment model corresponding to the ith refrigeration equipment.
Further, the data drift mentioned in the embodiments of the present application can be understood as: the parameter value is misplaced between the two data; i.e. the x-th parameter value in the first data (e.g. model tag data) is equal to the x-y-th parameter value, or x + y-th parameter value, in the second data (e.g. model output data). Wherein x and y are positive integers, and the first data and the second data both comprise F parameter values, F is a positive integer, and when the x-th parameter value in the first data is equal to the x-y-th parameter value in the second data, x is [1+y, F ]; and in the case where the x-th parameter value in the first data is equal to the x+y-th parameter value in the second data, x e 1, f-y. For example, let y=1, f=5, the first data contains 12345 these 5 parameter values, and the second data contains 23456 these 5 parameter values, in which case it may be determined that there is a data drift between the first data and the second data. Alternatively, the data drift mentioned in the embodiments of the present application can be understood as: the result of multiplying the second data by a certain coefficient is equal to the case of the first data. For example, the first data is [1,2,3], the second data is [0.5,1,1.5], and since the second data multiplied by 2 is [1,2,3], which is identical to the first data, a data drift can be considered to exist between the first data and the second data.
In addition, when the computer device performs identification calibration on the model parameters of the ith initial equipment model according to the data drift detection result to obtain the target equipment model corresponding to the ith refrigeration equipment, the computer device may specifically execute the following steps: if the data drift detection result indicates that data drift exists between the model label data and the model output data, adding a correction coefficient to the model parameters of the ith initial equipment model so as to calibrate the corresponding model parameters and obtain a target equipment model corresponding to the ith refrigeration equipment; alternatively, the model parameters of the ith initial equipment model may be updated to calibrate the corresponding model parameters, thereby obtaining the target equipment model corresponding to the ith refrigeration equipment. If the data drift detection result indicates that no data drift exists between the model label data and the model output data, the model parameters of the ith initial equipment model are kept unchanged, and a target equipment model corresponding to the ith refrigeration equipment is obtained, namely the target equipment model is the ith initial equipment model.
Based on the above description, exemplary: when the model parameters of the initial cooling water pump model are identified and calibrated, an equipment-level verification model which corresponds to the model parameters and takes field historical operation data as boundary conditions is established. Wherein the input of the fluid inlet interface of the initial cooling water pump model may be designated as physical information (e.g., physical parameters such as flow rate) of the upstream fluid entering the water pump, and the output of the fluid outlet interface of the initial cooling water pump model may be designated as physical information of the downstream fluid exiting the water pump, to generate the equipment level verification model. In addition, the model input interface of the initial cooling water pump model can be used for inputting the rotating speed (which can be converted through the motor operating frequency) in the operating data generated by the cooling water pump history, so that the rotating speed can be extracted from the operating data generated by the cooling water pump history to construct model input data; the model output interface of the initial cooling water pump model can be used for outputting the power of the cooling water pump, so that the power required to be output by the model output interface at least one time point can be extracted from the operation data generated by the history of the cooling water pump to construct model tag data so as to be compared with the model output after operation. After the equipment-level verification model is verified, further, the equipment-level verification model of the water pump is operated based on the model input data, so that model output data of the water pump under specified input boundary conditions (namely model input data) is obtained, wherein the model output data comprises the power actually output by the model output interface at least one time point; further, the model output data and the model output power can be compared with field measured data (i.e., model tag data). If the parameter value has the same change trend but has integral drift in value, the model parameters can be reversely corrected based on measured data by adding correction coefficients to the model parameters in the model codes, so that the running result of the model can be more fit with the actual working condition, and a foundation is laid for the subsequent system optimization work.
It will be appreciated that the process of identifying and calibrating model parameters of the initial equipment model corresponding to the remaining refrigeration equipment is similar to the process of identifying and calibrating model parameters of the initial cooling water pump model, except for the differences in the calibration target and the required model parameters. For example, the initial equipment model corresponding to the cooling tower mainly takes power and cooling water outlet temperature as calibration targets; the initial equipment model corresponding to the heat exchanger mainly takes the outlet temperature of cooling water and chilled water as a calibration target; the initial equipment model corresponding to the water chiller mainly uses power, cooling water and chilled water outlet temperature as calibration targets, and the like. Parameters required for each initial equipment model can be obtained by consulting a user help document on the Modelica Buildings Library official network and fitting with reference to the mathematical model of each model based on the field historic operational data. The more abundant the data volume, the more comprehensive the working condition that covers, the better the effect of calibration, the more can the true running state of refrigerating system be reflected to the model.
And S304, connecting the target equipment models corresponding to the refrigeration equipment according to the equipment configuration information of the refrigeration system to obtain a virtual simulation system corresponding to the refrigeration system.
In one embodiment, after the virtual simulation system is obtained, the virtual simulation system can be directly put on line, so that other users can test the AI energy-saving algorithm by downloading the virtual simulation system and using the virtual simulation system.
In another embodiment, considering that the virtual simulation system has complex software dependencies (software dependence), for it to function properly, the user needs to install multiple software, such as a compiler and model library of the simulation engine (Modelica Buildings Library); wherein, if the simulation engine is a Modelica engine, the compiler of the simulation engine is a Modelica compiler (e.g., dymola (a Modelica-supporting compiler) or OpenModelica (a Modelica-supporting compiler)). Users who are less familiar with building energy system simulations (e.g., researchers focusing on AI control and optimization) may not install such software, in which case the complex software dependencies that virtual simulation systems have may affect the availability of software and the audience of use. In order to solve the key pain point, the embodiment of the application provides a method for packaging and packaging needed software in a container, so that a user of the virtual simulation system can run and call the virtual simulation system constructed by the embodiment of the application under any operating system without installing any software (including Modelica) in advance, thereby using the virtual simulation system for debugging, training and comparing the AI energy-saving algorithm of the user. Based on this, after the virtual simulation system is obtained through step S304, the computer device may further execute subsequent step S305 to implement the containerization process of the virtual simulation system.
S305, obtaining each dependency term required by the virtual simulation system in operation, and carrying out containerization processing on each obtained dependency term and the virtual simulation system to obtain an image file of the target container.
Wherein the target container comprises at least: each dependent item, a virtual simulation system and a container interaction interface; the container interaction interface is an interface for interacting with the virtual simulation system, which may be, for example, a RESTFUL API (an interface for securely exchanging information over the Internet). The various dependencies mentioned herein may include, but are not limited to: operating environment, libraries, environment variables, configuration files, etc. of the virtual simulation system; wherein the library may include a plurality of models and other functions, and the configuration file may include configuration information of the virtual simulation system, which may be used to indicate the models and functions, etc., that the virtual simulation system needs to call. It should be understood that the virtual simulation system is essentially a piece of code (i.e., an application program), and each dependency item and the virtual simulation system are subjected to container processing, which is understood to be that each dependency item and the code used to form the virtual simulation system are subjected to container processing, so as to obtain an image file of the target container.
The image file of the target container refers to a file for creating the target container, and the target container is a running instance of the image file. To facilitate a better understanding of the relationship between the image file and the target container, the image file may be analogized to a class in object-oriented programming, which is a read-only template that contains all the content required to run the virtual simulation system, including code, running environment, libraries, environment variables, configuration files, and the like; the user may create a new container based on an image file as if the user could create a new object based on a class. The image file can be created, deleted and updated, and can be shared into other container environments. The target container can be analogically to an object in object-oriented programming, which is a running instance of an image file; the user may start, stop, move or delete a container just as the user may operate an object.
In particular implementations, the computer device may select a Docker container as the containerization tool, thereby enabling containerization of individual dependent items and virtual simulation systems through the containerization tool. A so-called Docker container is a container built based on lightweight virtualization technology that automates the deployment of applications to run applications in a self-sufficient container. Moreover, the Docker container can run in various environments, such as a local machine and a cloud computing platform, and the operating systems of these environments may be any operating system, such as Linux (an open-source operating system), windows (an operating system developed based on a graphical user interface), or macOS (a graphical interface operating system); it can be seen that the Docker container has a cross-platform (cross-system) feature that makes it well suited for creating and deploying software applications. One major advantage due to the Docker container is that: it contains all the dependencies required to run the application, so it can ensure that the application behaves consistently in different environments, eliminating the problem of "can run on I machine why it cannot run on you machine", greatly improving development and deployment efficiency. Furthermore, the ease of migration of the Docker container is another significant advantage. It is convenient to migrate from the development environment to the production environment, or from one cloud platform to another. The user no longer needs to worry about configuration and management dependencies in different environments, only needs to build a corresponding Docker container and then run it wherever needed. When a user installs a Docker on their host computing resource and downloads the Docker container (i.e., the target container) in which the virtual simulation system constructed in accordance with the embodiments of the present application is located, the user may use a single command to construct and deploy an operating environment (RTE), and the user may interact with the virtual simulation system in the target container through the restf ul API defined in accordance with the embodiments of the present application, as shown in fig. 4 a. This approach not only simplifies the deployment and management of the virtual simulation system, but also allows users to focus more on their primary tasks-developing and optimizing their AI power saving algorithms, rather than spending a significant amount of time and effort in handling the configuration and management of the virtual simulation system.
Specifically, the computer device uses a container tool, namely a Docker container, to perform container processing on each obtained dependency item and the virtual simulation system, and a specific process of obtaining the image file of the target container may include: creating a text file (Dockerfile) comprising at least one file parameter; the file parameters mentioned herein refer to parameters for creating an image file, which may include a series of commands and configuration parameters for automatically creating an image file. After the text file is created, each obtained dependent item and the virtual simulation system can be defined in the text file, and the defined text file is obtained; specifically, each obtained dependency item and a virtual simulation system can be directly added into the text file to obtain a defined text file; or adding the obtained identification of each dependent item and the virtual simulation system in the text file to obtain the defined text file. Then, a mirror image creation command (i.e. a dock build command) can be called to create a mirror image file of the target container by using the defined text file; it can be appreciated that if the text file after definition includes the identifier of each dependency item and the identifier of the virtual simulation system, the creation process includes the actions of downloading each dependency item according to each identifier, and building the operation environment required by the virtual simulation system based on each downloaded dependency item.
After the virtual simulation system is subjected to the containerization process in step S305 to obtain the image file of the target container, the user can download the image file and use the image file to create and run the target container on their machine, as shown in fig. 4 b; thus, they can run a virtual simulation system constructed using the embodiments of the present application without installing any dependencies. That is, for a user (i.e., a target user) who wants to use the virtual simulation system, the user can create a target container using the image file by downloading the image file, and operate the virtual simulation system by operating the target container; and in the running process of the virtual simulation system, the user can call the container interaction interface to interact with the virtual simulation system (as shown in the foregoing fig. 4 a) so as to obtain the data output by each target equipment model in the virtual simulation system, thereby debugging and optimizing the AI energy-saving algorithm according to the obtained data.
Optionally, when any user is considered to interact with the virtual simulation system by calling the container interaction interface, a plurality of commands can be written to call the container interaction interface, and data output by each target equipment model in the virtual simulation system are respectively obtained; based on the above, in order to improve the convenience and efficiency of data acquisition, the embodiment of the application can also perform standardized interface packaging on the target container. The standardized interface package has the following advantages: the user of the virtual simulation platform can use the same set of interaction language to call the standardized interface to interact with the virtual simulation system, so that the data output by each target equipment model in the virtual simulation system is uniformly acquired, and different commands are not required to be written for different target equipment models to acquire corresponding data. Based on this, the computer device may further perform the subsequent step S306 to implement standardized interface packaging for the target container.
S306, creating a simulation environment, and using the created simulation environment to perform standardized interface packaging on the target container to obtain a standardized interface.
The standardized interface has the capability of communicating with the container interaction interface in the target container, namely, the standardized interface can perform bottom interaction with the container interaction interface in the target container, so that after the container interaction interface acquires the data output by each target device model in the virtual simulation system, the standardized interface can acquire the data output by each target device model in the virtual simulation system from the container interaction interface based on the bottom interaction, and the acquired data is output to a user of the virtual simulation system. Therefore, the user of the virtual simulation system downloads the standardized interface under the condition of downloading the image file, so that the standardized interface is called to acquire the data output by each target equipment model in the virtual simulation system in the running process of the virtual simulation system. It is understood that the user may download the image file and the standardized interface at the same time, or may download the image file and the standardized interface sequentially, which is not limited.
In a specific implementation, the computer device may select OpenAI Gym as the encapsulation tool, thereby performing step S306 through the encapsulation tool. The so-called OpenAI Gym is an encapsulation tool implemented in Python (a cross-platform computer programming language) language, which can be used to encapsulate and standardize virtual simulation systems. The standardized interface obtained by carrying out standardized interface encapsulation through the OpenAI zym belongs to the OpenAI zym interface, and the OpenAI zym interface is a common interface in the field of building energy system optimization control, so that the standardized interface encapsulation of the target container can be realized by selecting the OpenAI zym, the learning cost of a user can be reduced by the standardized interface obtained by encapsulation, and the virtual simulation system constructed by the embodiment of the application can be quickly started. It should be appreciated that in other embodiments, the computer device may alternatively implement the standardized interface package for the target container using other packaging tools (such as BOPTSET (a packaging tool)), and the packaging tool is not limited by the embodiment of the present application. For convenience of explanation, openAI zym will be taken as an example of the encapsulation tool.
Specifically, the specific process of the computer device executing step S306 using the OpenAI zym encapsulation tool may include: a simulation environment is created which may be a new Gym environment and which is a Python class, interfaces that can be used to implement the Gym environment. In this class, a computer device may define a state space of the environment, an action space, and a dynamic behavior of the environment; the environment herein refers to a virtual simulation system, and the state space includes one or more states of each target device model in the virtual simulation system, which states are understood to be data output by the target device model; the action space includes one or more actions supportable by each target device model in the virtual simulation system, the actions may include input data to be input by each target device model in the virtual simulation system, and the actions are used for indicating to adjust the input data of the target device model to the input data included in the actions. In addition, two main methods of simulating an environment can be defined: reset method and step method; the rest method is used for resetting the state of the virtual simulation system to an initial state, and the step method is used for executing the action of calling the virtual simulation system, so that each target device model in the virtual simulation system is processed according to corresponding model input data, and a new state (namely new data) is output. Then, packaging the target container in a simulation environment to obtain a standardized interface; wherein, the encapsulation of the target container in the simulation environment can be understood as: integrating the simulation environment and the target container; the virtual simulation system in the target container is encapsulated by OpenAI zym into an "Environment" object, which provides basic methods, such as reset method and step method, for controlling the simulation.
Since the target container includes a container interaction interface (RESTful API), by encapsulating the target container in the simulation environment, it is possible to integrate the container interaction interface (RESTful API) that interacts with the virtual simulation system in the target container with the environment interface of the simulation environment (i.e., gym environment) to implement one RESTful API in the simulation environment. Because the RESTful API can interact with the virtual simulation system running in the target container through HTTP (hypertext transfer protocol) requests, the user can interact with the virtual simulation system by calling the standardized interface in Python environment using the standardized interaction language of Gym, thereby implementing actions (including model input data required to be input by each target device model in the virtual simulation system) output by the AI energy saving algorithm, inputting the actions into the virtual simulation system, and acquiring data (states) output by each target device model in the virtual simulation system, so as to optimize the AI energy saving algorithm based on the states, as shown in fig. 4 c. It follows that this greatly simplifies the development and testing process of the AI energy-saving algorithm, so that users need only pay attention to how to improve their AI energy-saving algorithm, without spending a great deal of time and effort in dealing with the details of interacting with the virtual simulation system.
According to the embodiment of the application, the standardized virtual simulation system corresponding to the refrigeration equipment can be automatically constructed by adopting the latest generation of building energy consumption simulation tool Modelica and the parameter identification method based on the operation data, and the virtual simulation system constructed by the method can effectively improve the simulation precision. In addition, the virtual simulation system can be used for developing and comparing different AI energy-saving algorithms, so that the cost and risk required by verifying the AI energy-saving algorithm can be reduced, a developer of the AI energy-saving algorithm can be helped to rapidly compare and iterate different AI energy-saving control algorithms, and the development efficiency is improved. Furthermore, by containerizing the virtual simulation system and encapsulating the standardized interface by using an encapsulation tool, a user can run the virtual simulation system without installing any dependency and interact with the virtual simulation system by using a uniform standardized interface; therefore, aiming at the virtual simulation system, a standardized interaction interface (OpenAI Gym or BOPTS SET) and a containerized thought are adopted, so that a user can conveniently call the virtual simulation system, and the use convenience of the virtual simulation system is improved.
Based on the description of the embodiment of the virtual simulation system generating method based on the refrigerating system, the embodiment of the application also discloses a virtual simulation system generating device based on the refrigerating system; the refrigeration system-based virtual simulation system generation apparatus may be a computer program (including one or more instructions) running in a computer device, and the refrigeration system-based virtual simulation system generation apparatus may perform the steps of the method flow shown in fig. 2 or 3. Referring to fig. 5, the virtual simulation system generating apparatus based on the refrigeration system may operate the following units:
A modeling unit 501, configured to perform simulation modeling on each refrigeration device in a refrigeration system to obtain an initial device model corresponding to each refrigeration device, where one refrigeration device corresponds to one initial device model;
the processing unit 502 is configured to obtain upstream and downstream boundary conditions of each initial equipment model, where the upstream and downstream boundary conditions of any initial equipment model are determined according to physical information of upstream and downstream fluids of the corresponding refrigeration equipment; wherein the upstream and downstream boundary conditions of the initial equipment model include: information required to run the corresponding initial equipment model;
the processing unit 502 is further configured to identify and calibrate model parameters of a corresponding initial equipment model based on operation data generated by the history of each refrigeration equipment and upstream and downstream boundary conditions of the corresponding initial equipment model, so as to obtain a target equipment model corresponding to each refrigeration equipment;
the processing unit 502 is further configured to connect, according to the device configuration information of the refrigeration system, the target device models corresponding to the refrigeration devices to obtain a virtual simulation system corresponding to the refrigeration system.
In one embodiment, when the processing unit 502 is configured to perform identification calibration on model parameters of the corresponding initial equipment model based on the operation data generated by the history of each refrigeration equipment and the upstream and downstream boundary conditions of the corresponding initial equipment model, to obtain the target equipment model corresponding to each refrigeration equipment, the processing unit may be specifically configured to:
Taking an initial equipment model corresponding to the ith refrigeration equipment as the ith initial equipment model, wherein I is E [1, I ], and I is the number of the refrigeration equipment in the refrigeration system;
constructing an equipment level verification model corresponding to the ith initial equipment model by adopting the ith initial equipment model and upstream and downstream boundary conditions of the ith initial equipment model; wherein the ith initial device model operates with operation of the device level verification model;
and according to the equipment-level verification model and the operation data generated by the ith refrigeration equipment history, identifying and calibrating the model parameters of the ith initial equipment model to obtain a target equipment model corresponding to the ith refrigeration equipment.
In another embodiment, when the processing unit 502 is configured to perform identification calibration on the model parameters of the ith initial equipment model according to the equipment-level verification model and the operation data generated by the ith refrigeration equipment history, to obtain the target equipment model corresponding to the ith refrigeration equipment, the processing unit may be specifically configured to:
obtaining model input data of the ith initial equipment model from operation data generated by the ith refrigeration equipment history, and obtaining data to be output by the ith initial equipment model under the model input data as model tag data;
Controlling the equipment-level verification model to operate according to the model input data, and acquiring data actually output by the ith initial equipment model as model output data in the operation process of the equipment-level verification model;
and identifying and calibrating the model parameters of the ith initial equipment model according to the model label data and the model output data to obtain a target equipment model corresponding to the ith refrigeration equipment.
In another embodiment, the ith initial device model includes a model output interface; the model tag data includes: the model output interface outputs parameter values to be output at each of a plurality of time points; the model output data includes: the model output interface actually outputting parameter values at each of the plurality of time points;
correspondingly, when the processing unit 502 is configured to perform identification calibration on the model parameters of the ith initial equipment model according to the model tag data and the model output data to obtain the target equipment model corresponding to the ith refrigeration equipment, the processing unit may be specifically configured to:
according to each parameter value in the model tag data, determining a parameter value change trend corresponding to the model tag data; determining a parameter value change trend corresponding to the model output data according to each parameter value in the model output data;
Carrying out consistency check on the determined two parameter value change trends to obtain a consistency check result;
and according to the consistency verification result, identifying and calibrating the model parameters of the ith initial equipment model to obtain a target equipment model corresponding to the ith refrigeration equipment.
In another embodiment, when the processing unit 502 is configured to perform identification calibration on the model parameters of the ith initial equipment model according to the consistency check result to obtain the target equipment model corresponding to the ith refrigeration equipment, the processing unit may be specifically configured to:
if the consistency check result indicates that the two parameter value change trends have consistency, carrying out data drift detection between the model tag data and the model output data, and carrying out identification calibration on the model parameters of the ith initial equipment model according to the data drift detection result to obtain a target equipment model corresponding to the ith refrigeration equipment;
if the consistency check result indicates that the two parameter value change trends do not have consistency, determining that the model parameters of the ith initial equipment model are abnormal, and carrying out simulation modeling on the ith refrigeration equipment again to obtain a target equipment model corresponding to the ith refrigeration equipment.
In another embodiment, when the processing unit 502 is configured to perform identification calibration on the model parameters of the ith initial equipment model according to the data drift detection result to obtain the target equipment model corresponding to the ith refrigeration equipment, the processing unit may be specifically configured to:
if the data drift detection result indicates that data drift exists between the model label data and the model output data, a correction coefficient is added for the model parameters of the ith initial equipment model so as to calibrate the corresponding model parameters and obtain a target equipment model corresponding to the ith refrigeration equipment;
if the data drift detection result indicates that no data drift exists between the model label data and the model output data, the model parameters of the ith initial equipment model are kept unchanged, and the target equipment model corresponding to the ith refrigeration equipment is obtained.
In another embodiment, when the modeling unit 501 is configured to perform simulation modeling on each refrigeration device in the refrigeration system to obtain an initial device model corresponding to each refrigeration device, the modeling unit may be specifically configured to:
obtaining a plurality of candidate equipment models corresponding to the ith refrigeration equipment in the refrigeration system, wherein each candidate equipment model is obtained by carrying out simulation modeling on the ith refrigeration equipment, and different candidate equipment models correspond to different model input data; i is E [1, I ], wherein I is the number of refrigeration equipment in the refrigeration system;
Selecting one candidate equipment model from the plurality of candidate equipment models according to the model input data indicated by the simulation demand; the model parameters of the selected candidate equipment model are obtained, and the obtained model parameters are determined based on at least one of design data of the ith refrigeration equipment and operation data generated by corresponding refrigeration equipment histories;
and the obtained model parameters are built in the selected candidate equipment models to obtain the initial equipment model corresponding to the ith refrigeration equipment.
In another embodiment, the processing unit 502 may be further configured to:
acquiring each dependency item required by the virtual simulation system in operation;
performing containerization processing on each obtained dependency item and the virtual simulation system to obtain an image file of a target container; wherein the target container comprises at least: the dependency items, the virtual simulation system and the container interaction interface;
the user creates the target container by downloading the image file, and runs the virtual simulation system by running the target container; and in the running process of the virtual simulation system, the user calls the container interaction interface to interact with the virtual simulation system so as to acquire data output by each target equipment model in the virtual simulation system.
In another embodiment, when the processing unit 502 is configured to perform containerization processing on each acquired dependency term and the virtual simulation system to obtain an image file of the target container, the processing unit may be specifically configured to:
creating a text file, wherein the text file comprises at least one file parameter, and the file parameter refers to a parameter used for creating an image file;
defining each obtained dependency item and the virtual simulation system in the text file to obtain a defined text file;
and calling an image creation command to create an image file of the target container by using the defined text file.
In another embodiment, the processing unit 502 may be further configured to:
creating a simulation environment;
carrying out standardized interface encapsulation on the target container by using the created simulation environment to obtain a standardized interface, wherein the standardized interface has the capability of communicating with a container interaction interface in the target container;
and the user downloads the standardized interface under the condition of downloading the image file so as to call the standardized interface to acquire data output by each target equipment model in the virtual simulation system in the running process of the virtual simulation system.
According to another embodiment of the present application, each unit in the virtual simulation system generating apparatus based on a refrigeration system shown in fig. 5 may be separately or completely combined into one or several other units, or some unit(s) thereof may be further split into a plurality of units with smaller functions, which may achieve the same operation without affecting the implementation of the technical effects of the embodiments of the present application. The above units are divided based on logic functions, and in practical applications, the functions of one unit may be implemented by a plurality of units, or the functions of a plurality of units may be implemented by one unit. In other embodiments of the present application, the virtual simulation system generating apparatus based on the refrigeration system may also include other units, and in practical applications, these functions may also be implemented with assistance of other units, and may be implemented by cooperation of multiple units.
According to another embodiment of the present application, a refrigeration system-based virtual simulation system generation apparatus as shown in fig. 5 may be constructed by running a computer program (including one or more instructions) capable of executing the steps involved in the respective methods as shown in fig. 2 or 3 on a general-purpose computing device such as a computer including a processing element such as a Central Processing Unit (CPU), a random access storage medium (RAM), a read only storage medium (ROM), and a storage element, and a refrigeration system-based virtual simulation system generation method of an embodiment of the present application may be implemented. The computer program may be recorded on, for example, a computer readable storage medium, and loaded into and executed by the computing device described above.
According to the embodiment of the application, simulation modeling can be carried out on each refrigeration device in the refrigeration system to obtain the initial device model corresponding to each refrigeration device, physical information of upstream and downstream fluid of each refrigeration device is respectively obtained, the determined upstream and downstream boundary conditions of the corresponding initial device model are used for ensuring that each initial device model can normally operate based on the obtained upstream and downstream boundary conditions, so that model parameters of the corresponding initial device model can be identified and calibrated based on operation data generated by histories of each refrigeration device and the upstream and downstream boundary conditions of the corresponding initial device model respectively to obtain the target device model corresponding to each refrigeration device, the operation state of the corresponding refrigeration device can be accurately reflected by each target device model, the self-adaptive characteristic is realized, and a relatively accurate virtual simulation system can be automatically generated by connecting each target device.
Based on the description of the method embodiment and the device embodiment, the embodiment of the application also provides a computer device. Referring to fig. 6, the computer device includes at least a processor 601, an input interface 602, an output interface 603, and a computer storage medium 604. Wherein the processor 601, input interface 602, output interface 603, and computer storage medium 604 within a computer device may be connected by a bus or other means. The computer storage medium 604 may be stored in a memory of a computer device, the computer storage medium 604 being configured to store a computer program comprising one or more instructions, and the processor 601 being configured to execute one or more instructions of the computer program stored in the computer storage medium 604. The processor 601 (or CPU (Central Processing Unit, central processing unit)) is a computing core and a control core of a computer device adapted to implement one or more instructions, in particular to load and execute one or more instructions to implement a corresponding method flow or a corresponding function.
In one embodiment, the processor 601 according to the embodiment of the present application may be configured to perform a series of virtual simulation system generation based on a refrigeration system, and specifically includes: performing simulation modeling on each refrigeration device in a refrigeration system to obtain an initial device model corresponding to each refrigeration device, wherein one refrigeration device corresponds to one initial device model; respectively acquiring the upstream and downstream boundary conditions of each initial equipment model, wherein the upstream and downstream boundary conditions of any initial equipment model are determined according to the physical information of upstream and downstream fluid of corresponding refrigeration equipment; wherein the upstream and downstream boundary conditions of the initial equipment model include: information required to run the corresponding initial equipment model; identifying and calibrating model parameters of the corresponding initial equipment model based on operation data generated by the histories of the refrigeration equipment and upstream and downstream boundary conditions of the corresponding initial equipment model respectively to obtain a target equipment model corresponding to the refrigeration equipment; and connecting the target equipment models corresponding to the refrigeration equipment according to the equipment configuration information of the refrigeration system to obtain a virtual simulation system corresponding to the refrigeration system, and the like.
The embodiment of the application also provides a computer storage medium (Memory), which is a Memory device in the computer device and is used for storing computer programs and data. It is understood that the computer storage media herein may include both built-in storage media in a computer device and extended storage media supported by the computer device. The computer storage media provides storage space that stores an operating system of the computer device. Also stored in the memory space is a computer program comprising one or more instructions, which may be one or more program codes, adapted to be loaded and executed by the processor 601. The computer storage medium herein may be a high-speed RAM memory or a non-volatile memory (non-volatile memory), such as at least one magnetic disk memory; alternatively, it may be at least one computer storage medium located remotely from the aforementioned processor.
In one embodiment, one or more instructions stored in a computer storage medium may be loaded and executed by a processor to implement the corresponding steps in the method embodiments described above with respect to FIG. 2 or FIG. 3; in particular implementations, one or more instructions in a computer storage medium may be loaded by a processor and perform the steps of:
Performing simulation modeling on each refrigeration device in a refrigeration system to obtain an initial device model corresponding to each refrigeration device, wherein one refrigeration device corresponds to one initial device model;
respectively acquiring the upstream and downstream boundary conditions of each initial equipment model, wherein the upstream and downstream boundary conditions of any initial equipment model are determined according to the physical information of upstream and downstream fluid of corresponding refrigeration equipment; wherein the upstream and downstream boundary conditions of the initial equipment model include: information required to run the corresponding initial equipment model;
identifying and calibrating model parameters of the corresponding initial equipment model based on operation data generated by the histories of the refrigeration equipment and upstream and downstream boundary conditions of the corresponding initial equipment model respectively to obtain a target equipment model corresponding to the refrigeration equipment;
and connecting the target equipment models corresponding to the refrigeration equipment according to the equipment configuration information of the refrigeration system to obtain a virtual simulation system corresponding to the refrigeration system.
In one embodiment, when the model parameters of the corresponding initial equipment model are identified and calibrated based on the operation data generated by the history of each refrigeration equipment and the upstream and downstream boundary conditions of the corresponding initial equipment model respectively to obtain the target equipment model corresponding to each refrigeration equipment, the one or more instructions may be loaded and specifically executed by the processor:
Taking an initial equipment model corresponding to the ith refrigeration equipment as the ith initial equipment model, wherein I is E [1, I ], and I is the number of the refrigeration equipment in the refrigeration system;
constructing an equipment level verification model corresponding to the ith initial equipment model by adopting the ith initial equipment model and upstream and downstream boundary conditions of the ith initial equipment model; wherein the ith initial device model operates with operation of the device level verification model;
and according to the equipment-level verification model and the operation data generated by the ith refrigeration equipment history, identifying and calibrating the model parameters of the ith initial equipment model to obtain a target equipment model corresponding to the ith refrigeration equipment.
In another embodiment, when the model parameters of the ith initial equipment model are identified and calibrated according to the equipment-level verification model and the operation data generated by the ith refrigeration equipment history to obtain the target equipment model corresponding to the ith refrigeration equipment, the one or more instructions may be loaded and specifically executed by the processor:
obtaining model input data of the ith initial equipment model from operation data generated by the ith refrigeration equipment history, and obtaining data to be output by the ith initial equipment model under the model input data as model tag data;
Controlling the equipment-level verification model to operate according to the model input data, and acquiring data actually output by the ith initial equipment model as model output data in the operation process of the equipment-level verification model;
and identifying and calibrating the model parameters of the ith initial equipment model according to the model label data and the model output data to obtain a target equipment model corresponding to the ith refrigeration equipment.
In another embodiment, the ith initial device model includes a model output interface; the model tag data includes: the model output interface outputs parameter values to be output at each of a plurality of time points; the model output data includes: the model output interface actually outputting parameter values at each of the plurality of time points;
correspondingly, when the model parameters of the ith initial equipment model are identified and calibrated according to the model label data and the model output data to obtain the target equipment model corresponding to the ith refrigeration equipment, the one or more instructions can be loaded and specifically executed by the processor:
According to each parameter value in the model tag data, determining a parameter value change trend corresponding to the model tag data; determining a parameter value change trend corresponding to the model output data according to each parameter value in the model output data;
carrying out consistency check on the determined two parameter value change trends to obtain a consistency check result;
and according to the consistency verification result, identifying and calibrating the model parameters of the ith initial equipment model to obtain a target equipment model corresponding to the ith refrigeration equipment.
In another embodiment, when the model parameters of the ith initial equipment model are identified and calibrated according to the consistency check result to obtain the target equipment model corresponding to the ith refrigeration equipment, the one or more instructions may be loaded and specifically executed by the processor:
if the consistency check result indicates that the two parameter value change trends have consistency, carrying out data drift detection between the model tag data and the model output data, and carrying out identification calibration on the model parameters of the ith initial equipment model according to the data drift detection result to obtain a target equipment model corresponding to the ith refrigeration equipment;
If the consistency check result indicates that the two parameter value change trends do not have consistency, determining that the model parameters of the ith initial equipment model are abnormal, and carrying out simulation modeling on the ith refrigeration equipment again to obtain a target equipment model corresponding to the ith refrigeration equipment.
In another embodiment, when the model parameters of the ith initial equipment model are identified and calibrated according to the data drift detection result to obtain the target equipment model corresponding to the ith refrigeration equipment, the one or more instructions may be loaded and specifically executed by the processor:
if the data drift detection result indicates that data drift exists between the model label data and the model output data, a correction coefficient is added for the model parameters of the ith initial equipment model so as to calibrate the corresponding model parameters and obtain a target equipment model corresponding to the ith refrigeration equipment;
if the data drift detection result indicates that no data drift exists between the model label data and the model output data, the model parameters of the ith initial equipment model are kept unchanged, and the target equipment model corresponding to the ith refrigeration equipment is obtained.
In another embodiment, when performing simulation modeling on each refrigeration device in the refrigeration system to obtain an initial device model corresponding to each refrigeration device, the one or more instructions may be loaded and specifically executed by the processor:
obtaining a plurality of candidate equipment models corresponding to the ith refrigeration equipment in the refrigeration system, wherein each candidate equipment model is obtained by carrying out simulation modeling on the ith refrigeration equipment, and different candidate equipment models correspond to different model input data; i is E [1, I ], wherein I is the number of refrigeration equipment in the refrigeration system;
selecting one candidate equipment model from the plurality of candidate equipment models according to the model input data indicated by the simulation demand; the model parameters of the selected candidate equipment model are obtained, and the obtained model parameters are determined based on at least one of design data of the ith refrigeration equipment and operation data generated by corresponding refrigeration equipment histories;
and the obtained model parameters are built in the selected candidate equipment models to obtain the initial equipment model corresponding to the ith refrigeration equipment.
In another embodiment, the one or more instructions may be loaded by a processor and executed in particular:
Acquiring each dependency item required by the virtual simulation system in operation;
performing containerization processing on each obtained dependency item and the virtual simulation system to obtain an image file of a target container; wherein the target container comprises at least: the dependency items, the virtual simulation system and the container interaction interface;
the user creates the target container by downloading the image file, and runs the virtual simulation system by running the target container; and in the running process of the virtual simulation system, the user calls the container interaction interface to interact with the virtual simulation system so as to acquire data output by each target equipment model in the virtual simulation system.
In another embodiment, when the obtained dependency items and the virtual simulation system are subjected to containerization processing to obtain an image file of the target container, the one or more instructions may be loaded and specifically executed by the processor:
creating a text file, wherein the text file comprises at least one file parameter, and the file parameter refers to a parameter used for creating an image file;
Defining each obtained dependency item and the virtual simulation system in the text file to obtain a defined text file;
and calling an image creation command to create an image file of the target container by using the defined text file.
In another embodiment, the one or more instructions may be loaded by a processor and executed in particular:
creating a simulation environment;
carrying out standardized interface encapsulation on the target container by using the created simulation environment to obtain a standardized interface, wherein the standardized interface has the capability of communicating with a container interaction interface in the target container;
and the user downloads the standardized interface under the condition of downloading the image file so as to call the standardized interface to acquire data output by each target equipment model in the virtual simulation system in the running process of the virtual simulation system.
According to the embodiment of the application, simulation modeling can be carried out on each refrigeration device in the refrigeration system to obtain the initial device model corresponding to each refrigeration device, physical information of upstream and downstream fluid of each refrigeration device is respectively obtained, the determined upstream and downstream boundary conditions of the corresponding initial device model are used for ensuring that each initial device model can normally operate based on the obtained upstream and downstream boundary conditions, so that model parameters of the corresponding initial device model can be identified and calibrated based on operation data generated by histories of each refrigeration device and the upstream and downstream boundary conditions of the corresponding initial device model respectively to obtain the target device model corresponding to each refrigeration device, the operation state of the corresponding refrigeration device can be accurately reflected by each target device model, the self-adaptive characteristic is realized, and a relatively accurate virtual simulation system can be automatically generated by connecting each target device.
It should be noted that, according to an aspect of the present application, there is also provided a computer program product or a computer program, which comprises one or more instructions stored in a computer storage medium. The processor of the computer device reads one or more instructions from the computer storage medium and executes the one or more instructions to cause the computer device to perform the methods provided in the various alternatives to the method embodiment aspects illustrated in fig. 2 or 3 described above. It should be understood that the foregoing disclosure is only illustrative of the preferred embodiments of the present application and is not to be construed as limiting the scope of the application, which is defined by the appended claims.
Claims (16)
1. A method for generating a virtual simulation system based on a refrigeration system, comprising:
performing simulation modeling on each refrigeration device in a refrigeration system to obtain an initial device model corresponding to each refrigeration device, wherein one refrigeration device corresponds to one initial device model;
respectively acquiring the upstream and downstream boundary conditions of each initial equipment model, wherein the upstream and downstream boundary conditions of any initial equipment model are determined according to the physical information of upstream and downstream fluid of corresponding refrigeration equipment; wherein the upstream and downstream boundary conditions of the initial equipment model include: information required to run the corresponding initial equipment model;
Identifying and calibrating model parameters of the corresponding initial equipment model based on operation data generated by the histories of the refrigeration equipment and upstream and downstream boundary conditions of the corresponding initial equipment model respectively to obtain a target equipment model corresponding to the refrigeration equipment;
and connecting the target equipment models corresponding to the refrigeration equipment according to the equipment configuration information of the refrigeration system to obtain a virtual simulation system corresponding to the refrigeration system.
2. The method as set forth in claim 1, wherein said identifying and calibrating model parameters of the corresponding initial equipment model based on the operation data generated by the history of each refrigeration equipment and the upstream and downstream boundary conditions of the corresponding initial equipment model to obtain the corresponding target equipment model of each refrigeration equipment includes:
taking an initial equipment model corresponding to the ith refrigeration equipment as the ith initial equipment model, wherein I is E [1, I ], and I is the number of the refrigeration equipment in the refrigeration system;
constructing an equipment level verification model corresponding to the ith initial equipment model by adopting the ith initial equipment model and upstream and downstream boundary conditions of the ith initial equipment model; wherein the ith initial device model operates with operation of the device level verification model;
And according to the equipment-level verification model and the operation data generated by the ith refrigeration equipment history, identifying and calibrating the model parameters of the ith initial equipment model to obtain a target equipment model corresponding to the ith refrigeration equipment.
3. The method of claim 2, wherein the identifying and calibrating the model parameters of the i-th initial equipment model according to the equipment-level verification model and the operation data generated by the i-th refrigeration equipment history to obtain the target equipment model corresponding to the i-th refrigeration equipment comprises:
obtaining model input data of the ith initial equipment model from operation data generated by the ith refrigeration equipment history, and obtaining data to be output by the ith initial equipment model under the model input data as model tag data;
controlling the equipment-level verification model to operate according to the model input data, and acquiring data actually output by the ith initial equipment model as model output data in the operation process of the equipment-level verification model;
and identifying and calibrating the model parameters of the ith initial equipment model according to the model label data and the model output data to obtain a target equipment model corresponding to the ith refrigeration equipment.
4. The method of claim 3, wherein the ith initial device model comprises a model output interface; the model tag data includes: the model output interface outputs parameter values to be output at each of a plurality of time points; the model output data includes: the model output interface actually outputting parameter values at each of the plurality of time points;
identifying and calibrating the model parameters of the ith initial equipment model according to the model tag data and the model output data to obtain a target equipment model corresponding to the ith refrigeration equipment, wherein the method comprises the following steps of:
according to each parameter value in the model tag data, determining a parameter value change trend corresponding to the model tag data; determining a parameter value change trend corresponding to the model output data according to each parameter value in the model output data;
carrying out consistency check on the determined two parameter value change trends to obtain a consistency check result;
and according to the consistency verification result, identifying and calibrating the model parameters of the ith initial equipment model to obtain a target equipment model corresponding to the ith refrigeration equipment.
5. The method of claim 4, wherein the identifying and calibrating the model parameters of the ith initial equipment model according to the consistency check result to obtain the target equipment model corresponding to the ith refrigeration equipment comprises:
if the consistency check result indicates that the two parameter value change trends have consistency, carrying out data drift detection between the model tag data and the model output data, and carrying out identification calibration on the model parameters of the ith initial equipment model according to the data drift detection result to obtain a target equipment model corresponding to the ith refrigeration equipment;
if the consistency check result indicates that the two parameter value change trends do not have consistency, determining that the model parameters of the ith initial equipment model are abnormal, and carrying out simulation modeling on the ith refrigeration equipment again to obtain a target equipment model corresponding to the ith refrigeration equipment.
6. The method of claim 5, wherein the identifying and calibrating the model parameters of the i-th initial equipment model according to the data drift detection result to obtain the target equipment model corresponding to the i-th refrigeration equipment comprises:
If the data drift detection result indicates that data drift exists between the model label data and the model output data, a correction coefficient is added for the model parameters of the ith initial equipment model so as to calibrate the corresponding model parameters and obtain a target equipment model corresponding to the ith refrigeration equipment;
if the data drift detection result indicates that no data drift exists between the model label data and the model output data, the model parameters of the ith initial equipment model are kept unchanged, and the target equipment model corresponding to the ith refrigeration equipment is obtained.
7. The method of claim 1, wherein said performing simulation modeling on each refrigeration device in the refrigeration system to obtain an initial device model corresponding to each refrigeration device comprises:
obtaining a plurality of candidate equipment models corresponding to the ith refrigeration equipment in the refrigeration system, wherein each candidate equipment model is obtained by carrying out simulation modeling on the ith refrigeration equipment, and different candidate equipment models correspond to different model input data; i is E [1, I ], wherein I is the number of refrigeration equipment in the refrigeration system;
selecting one candidate equipment model from the plurality of candidate equipment models according to the model input data indicated by the simulation demand; the model parameters of the selected candidate equipment model are obtained, and the obtained model parameters are determined based on at least one of design data of the ith refrigeration equipment and operation data generated by corresponding refrigeration equipment histories;
And the obtained model parameters are built in the selected candidate equipment models to obtain the initial equipment model corresponding to the ith refrigeration equipment.
8. The method of claim 7, wherein determining the manner of model parameters of the selected candidate plant model based on at least one of design data of the ith refrigeration equipment and operational data historically produced by the corresponding refrigeration equipment comprises:
acquiring the operation time length of the ith refrigeration equipment;
if the running time length is greater than or equal to a time length threshold value, determining model parameters of the selected candidate equipment model based on running data generated by the ith refrigeration equipment history;
and if the operation time length is smaller than the time length threshold value, determining model parameters of the selected candidate equipment model based on design data of the ith refrigeration equipment.
9. The method of claim 7, wherein determining the manner of model parameters of the selected candidate plant model based on at least one of design data of the ith refrigeration equipment and operational data historically produced by the corresponding refrigeration equipment comprises:
carrying out consistency check on the design working condition of the ith refrigeration equipment and the operation working condition of the ith refrigeration equipment; the design working condition refers to a working condition indicated by design data of the ith refrigeration equipment, and the operation working condition refers to a working condition indicated by operation data historically generated by the ith refrigeration equipment;
If the design working condition and the operation working condition pass the consistency check, acquiring the difference degree between the design data and the operation data, screening effective data from the design data and the operation data according to the acquired difference degree, and determining model parameters of the selected candidate equipment model based on the effective data;
and if the design working condition and the operation working condition do not pass the consistency check, determining model parameters of the selected candidate equipment model based on the operation data.
10. The method of claim 9, wherein the screening the effective data from the design data and the operational data based on the obtained degree of difference comprises:
if the acquired difference is greater than or equal to a difference threshold, selecting the operation data from the design data and the operation data as effective data;
and if the acquired difference is smaller than the difference threshold, selecting the design data from the design data and the operation data as effective data.
11. The method of claim 1, wherein the method further comprises:
acquiring each dependency item required by the virtual simulation system in operation;
Performing containerization processing on each obtained dependency item and the virtual simulation system to obtain an image file of a target container; wherein the target container comprises at least: the dependency items, the virtual simulation system and the container interaction interface;
the user creates the target container by downloading the image file, and runs the virtual simulation system by running the target container; and in the running process of the virtual simulation system, the user calls the container interaction interface to interact with the virtual simulation system so as to acquire data output by each target equipment model in the virtual simulation system.
12. The method of claim 11, wherein the performing a containerization process on each of the obtained dependent items and the virtual simulation system to obtain an image file of the target container includes:
creating a text file, wherein the text file comprises at least one file parameter, and the file parameter refers to a parameter used for creating an image file;
defining each obtained dependency item and the virtual simulation system in the text file to obtain a defined text file;
And calling an image creation command to create an image file of the target container by using the defined text file.
13. The method of claim 11, wherein the method further comprises:
creating a simulation environment;
carrying out standardized interface encapsulation on the target container by using the created simulation environment to obtain a standardized interface, wherein the standardized interface has the capability of communicating with a container interaction interface in the target container;
and the user downloads the standardized interface under the condition of downloading the image file so as to call the standardized interface to acquire data output by each target equipment model in the virtual simulation system in the running process of the virtual simulation system.
14. A virtual simulation system generation apparatus based on a refrigeration system, comprising:
the modeling unit is used for performing simulation modeling on each refrigeration device in the refrigeration system to obtain an initial device model corresponding to each refrigeration device, wherein one refrigeration device corresponds to one initial device model;
the processing unit is used for respectively acquiring the upstream and downstream boundary conditions of each initial equipment model, and the upstream and downstream boundary conditions of any initial equipment model are determined according to the physical information of upstream and downstream fluid of the corresponding refrigeration equipment; wherein the upstream and downstream boundary conditions of the initial equipment model include: information required to run the corresponding initial equipment model;
The processing unit is further used for identifying and calibrating model parameters of the corresponding initial equipment model based on operation data generated by histories of the refrigeration equipment and upstream and downstream boundary conditions of the corresponding initial equipment model respectively to obtain a target equipment model corresponding to the refrigeration equipment;
and the processing unit is also used for connecting the target equipment models corresponding to the refrigeration equipment according to the equipment configuration information of the refrigeration system to obtain a virtual simulation system corresponding to the refrigeration system.
15. A computer device comprising an input interface and an output interface, further comprising: a processor and a computer storage medium;
wherein the processor is adapted to implement one or more instructions, the computer storage medium storing one or more instructions adapted to be loaded by the processor and to perform the refrigeration system-based virtual simulation system generation method of any of claims 1-12.
16. A computer storage medium storing one or more instructions adapted to be loaded by a processor and to perform the refrigeration system based virtual simulation system generation method of any of claims 1-12.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311113858.4A CN117034654A (en) | 2023-08-30 | 2023-08-30 | Virtual simulation system generation method based on refrigerating system and related equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311113858.4A CN117034654A (en) | 2023-08-30 | 2023-08-30 | Virtual simulation system generation method based on refrigerating system and related equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117034654A true CN117034654A (en) | 2023-11-10 |
Family
ID=88602337
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311113858.4A Pending CN117034654A (en) | 2023-08-30 | 2023-08-30 | Virtual simulation system generation method based on refrigerating system and related equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117034654A (en) |
-
2023
- 2023-08-30 CN CN202311113858.4A patent/CN117034654A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112577161B (en) | Air conditioner energy consumption model training method and air conditioner system control method | |
| Fierro | Design of an effective ontology and query processor enabling portable building applications | |
| US9798336B2 (en) | Building management system with linked thermodynamic models for HVAC equipment | |
| Wetter | Co-simulation of building energy and control systems with the Building Controls Virtual Test Bed | |
| US9429921B2 (en) | Method and system for energy control management | |
| CN110622139A (en) | Building management system development and control platform | |
| CN106528980A (en) | Water chilling unit model selecting method and device | |
| CN101427239A (en) | Building automation system data management | |
| Fu et al. | Equation-based object-oriented modeling and simulation of data center cooling systems | |
| Ucak et al. | The effects of load parameter dispersion and direct load control actions on aggregated load | |
| CN107120829A (en) | The control system and method for single water tank constant temperature water supply | |
| US20210190349A1 (en) | Building control system with zone grouping based on predictive models | |
| WO2021082511A1 (en) | Model training method and control parameter determination method and device | |
| CN117034654A (en) | Virtual simulation system generation method based on refrigerating system and related equipment | |
| CN116097628A (en) | System and method for evaluating and repairing data using data quality indicators | |
| CN103324600B (en) | The system of moving calculation module and operation method thereof | |
| CN101142559A (en) | Monitoring computer-controlled processes | |
| CN110398922B (en) | Building automatic control system and configuration method, device and equipment thereof | |
| Pruvost et al. | Ontology-based expert system for automated monitoring of building energy systems | |
| CN115238477A (en) | Simulation method of central air-conditioning system | |
| CN114593498A (en) | Air conditioner abnormity detection method, detection terminal, electronic equipment and storage medium | |
| Mörzinger et al. | A modular, holistic optimization approach for industrial appliances | |
| WO2021174779A1 (en) | Data pre-processing system and method, computer device, and readable storage medium | |
| Matsuda et al. | Modeling the existing cooling system to learn its behavior for Post-K supercomputer at RIKEN R-CCS | |
| de Andrade Pereira et al. | Enabling portable demand flexibility control applications in virtual and real buildings |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication |