A simulation method for compressed air energy storage system based on mechanism and data fusion

Abstract

This invention discloses a simulation method for compressed air energy storage systems based on mechanism and data fusion, comprising: modeling the compressed air energy storage system, constructing a mechanism model and a data-driven model; correcting the compressed air energy storage system model based on identification methods and deep learning algorithms; and performing simulation to optimize the scheduling of the compressed air energy storage system model. The mechanism- and data-driven simulation method provided by this invention achieves high-performance digital simulation of compressed air energy storage systems through the organic synergy of the mechanism model and the data-driven model. Using this method, static and dynamic models of complex compressed air energy storage systems can be established, effectively solving the problem of unclear structure of certain components in the compressed air energy storage system and the problem of rapid model calculation. It can provide model analysis tools for applications with high accuracy and real-time requirements, realize system characteristic analysis, and provide an effective method for system structure and operation and maintenance optimization.

Description

Technical Field

[0001] This invention relates to the field of energy storage system technology, specifically to a simulation method for compressed air energy storage systems based on mechanism and data fusion. Background Technology

[0002] With the increasing proportion of highly uncertain renewable energy power such as wind and solar in the power grid, large-scale energy storage technology is considered an indispensable means to ensure grid security, improve power quality, and promote the consumption of renewable energy. Compressed air energy storage (CAES) has advantages such as low pollution, low investment, flexible site selection, and large capacity, and has received high attention and rapid development in the energy storage field. It has broad application prospects in grid peak shaving and valley filling, renewable energy consumption, construction of independent power systems, emergency backup power, and provision of ancillary services. However, due to the limited number of commercially operational CAES systems and their short operational time, there is still a lack of technologies that can directly and effectively guide the design and operation and maintenance of CAES, which greatly restricts the development and widespread application of CAES.

[0003] Digital simulation is an important tool for the design and operation and maintenance analysis of compressed air energy storage systems. Improving the modeling and simulation technology of compressed air energy storage systems directly affects the performance of the entire system. Summary of the Invention

[0004] The purpose of this section is to outline some aspects of embodiments of the present invention and to briefly describe some preferred embodiments. Simplifications or omissions may be made in this section, as well as in the abstract and title of this application, to avoid obscuring the purpose of these documents; however, such simplifications or omissions should not be construed as limiting the scope of the invention.

[0005] In view of the above-mentioned problems, the present invention is proposed.

[0006] Therefore, the technical problem solved by this invention is that existing compressed air energy storage systems have limited quantity, short commissioning time, and unclear structure of certain components, and there is a lack of current technologies that can directly and effectively guide the design and operation and maintenance of compressed air energy storage systems, as well as the optimization problem of how to achieve rapid calculation of models.

[0007] To address the aforementioned technical problems, this invention provides the following technical solution: a simulation method for compressed air energy storage systems based on mechanism and data fusion, comprising:

[0008] Modeling of compressed air energy storage systems, constructing mechanistic models and data-driven models;

[0009] Model correction of compressed air energy storage system based on identification methods and deep learning algorithms;

[0010] Simulation was used to optimize the scheduling of the compressed air energy storage system model.

[0011] As a preferred embodiment of the mechanism- and data fusion-based simulation method for compressed air energy storage systems described in this invention, the modeling of the compressed air energy storage system includes a modeling preparation stage, a mechanism modeling stage, and a data-driven modeling stage.

[0012] As a preferred embodiment of the mechanism and data fusion-based simulation method for compressed air energy storage systems described in this invention, the modeling preparation stage includes the following steps: determining the target of the compressed air energy storage system simulation for design, operation, maintenance, or fault handling; defining the model object and scope, clarifying the basic components of the object to be studied, the operating condition range to be analyzed, etc.; and determining the input and output parameter set of the model using functional equipment as the basic unit.

[0013] As a preferred embodiment of the mechanism- and data fusion-based simulation method for compressed air energy storage systems described in this invention, the mechanism modeling stage includes the following steps: starting from the research objective, in order to simplify the model structure and reduce computational complexity, reasonable simplification assumptions need to be determined for the model; taking each functional device of CAES as the basic unit, based on relevant theories, the conservation equations based on mass, energy, and momentum equations and the physical property equations of the working fluid are determined; the compressed air energy storage system model structure is determined; and the compressed air energy storage system model parameters are determined.

[0014] As a preferred embodiment of the mechanism- and data fusion-based simulation method for compressed air energy storage systems described in this invention, the data-driven modeling stage includes the following steps: taking each functional device as the basic object, determining the data-driven model structure representing the input-output mapping relationship of the object based on the research objective; determining the data-driven model learning method according to the model structure and data characteristics; and learning the relevant parameters of the data-driven model through a large amount of actual operating data.

[0015] As a preferred embodiment of the mechanism- and data fusion-based simulation method for compressed air energy storage systems described in this invention, the steps for correcting the compressed air energy storage system model are as follows:

[0016] Acquire operational data from the compressed air energy storage system;

[0017] Determine whether the error of the mechanism model is greater than the set threshold;

[0018] If the error exceeds the set threshold, perform online identification of mechanism model parameters and update the mechanism model; otherwise, return to obtain the compressed air energy storage system operation data.

[0019] Determine whether the error of the data-driven model exceeds the set threshold;

[0020] If the error exceeds the set threshold, perform data-driven model training and updates; otherwise, return to continue acquiring compressed air energy storage system operation data.

[0021] As a preferred embodiment of the mechanism- and data fusion-based simulation method for compressed air energy storage systems described in this invention, the operating data of the compressed air energy storage system includes:

[0022] System-wide operating status parameter data;

[0023] Energy and mass transfer and conversion performance data of each device in the system;

[0024] Performance data for the entire system.

[0025] As a preferred embodiment of the mechanism- and data fusion-based simulation method for compressed air energy storage systems described in this invention, the steps of scheduling the compressed air energy storage system model are as follows:

[0026] Define the simulation task for the compressed air energy storage system;

[0027] The system calculates the storage space and computing power requirements of simulation tasks based on data-driven and mechanistic models online, and compares them with the currently available computing resources to determine whether the computing resources meet the needs of the simulation tasks. The system also determines the accuracy of the mechanistic and data-driven models by comparing the actual measured data with the model calculation data.

[0028] Determine whether the accuracy of the data-driven model is higher than that of the mechanistic model;

[0029] If so, then select the simulation data-driven model for simulation;

[0030] If not, then determine whether the computing power meets the computational requirements of the mechanism model;

[0031] If the conditions are met, the mechanistic model is selected for simulation; otherwise, the data-driven model is selected for simulation.

[0032] A computer device includes a memory and a processor, the memory storing a computer program, the processor executing the computer program to implement the steps of the method described above.

[0033] A computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the method described above.

[0034] The beneficial effects of this invention are as follows: The mechanism- and data-driven simulation method for compressed air energy storage systems provided by this invention achieves high-performance digital simulation of compressed air energy storage systems through the organic synergy of mechanism models and data-driven models. Using this method, static and dynamic models of complex compressed air energy storage systems can be established, effectively solving the problem of unclear structure of certain components in compressed air energy storage systems and the problem of rapid model calculation. It can provide model analysis tools for applications with high accuracy and real-time requirements, enabling system characteristic analysis and providing an effective method for system structure and operation and maintenance optimization. Attached Figure Description

[0035] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort. Wherein:

[0036] Figure 1 The overall flowchart of a simulation method for a compressed air energy storage system based on mechanism and data fusion is provided for the first embodiment of the present invention;

[0037] Figure 2 A schematic diagram of the modeling process for a simulation method of a compressed air energy storage system based on mechanism and data fusion, provided for the second embodiment of the present invention;

[0038] Figure 3 A schematic diagram of the model correction process for a simulation method of compressed air energy storage system based on mechanism and data fusion, provided for the second embodiment of the present invention;

[0039] Figure 4 A schematic diagram of the model scheduling process for a simulation method of compressed air energy storage system based on mechanism and data fusion, provided for the first embodiment of the present invention;

[0040] Figure 5 The diagram shows the internal structure of a computer device in a computer device that provides a simulation method for a compressed air energy storage system based on mechanism and data fusion, as shown in the first embodiment of the present invention.

[0041] Figure 6 The dynamic structure diagram of the speed regulation system during the start-up process of a simulation method for a compressed air energy storage system based on mechanism and data fusion, provided for the second embodiment of the present invention;

[0042] Figure 7 The rotational speed response curve is provided for a simulation method of a compressed air energy storage system based on mechanism and data fusion, which is provided for the second embodiment of the present invention. Detailed Implementation

[0043] To make the above-mentioned objects, features, and advantages of the present invention more apparent and understandable, specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of them. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the protection scope of the present invention.

[0044] Many specific details are set forth in the following description in order to provide a full understanding of the invention. However, the invention may also be practiced in other ways different from those described herein, and those skilled in the art can make similar extensions without departing from the spirit of the invention. Therefore, the invention is not limited to the specific embodiments disclosed below.

[0045] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in one embodiment" appearing in different places in this specification does not necessarily refer to the same embodiment, nor is it a single or selective embodiment that is mutually exclusive with other embodiments.

[0046] This invention is described in detail with reference to the schematic diagrams. When detailing the embodiments of this invention, for ease of explanation, the cross-sectional views illustrating the device structure may be partially enlarged, not adhering to the usual scale. Furthermore, the schematic diagrams are merely examples and should not be construed as limiting the scope of protection of this invention. In actual fabrication, the three-dimensional spatial dimensions of length, width, and depth should be included.

[0047] Furthermore, in the description of this invention, it should be noted that the terms "upper," "lower," "inner," and "outer," etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. These terms are used solely for the convenience of describing the invention and for simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on the invention. In addition, the terms "first," "second," or "third" are used for descriptive purposes only and should not be construed as indicating or implying relative importance.

[0048] Unless otherwise explicitly specified and limited, the terms "installation," "connection," and "joining" in this invention should be interpreted broadly. For example, they can refer to fixed connections, detachable connections, or integral connections; similarly, they can refer to mechanical connections, electrical connections, or direct connections, or indirect connections through an intermediate medium, or internal connections between two components. Those skilled in the art can understand the specific meaning of the above terms in this invention based on the specific circumstances.

[0049] Example 1

[0050] Reference Figure 1-5As an embodiment of the present invention, a simulation method for a compressed air energy storage system based on mechanism and data fusion is provided, comprising:

[0051] S1: Modeling of compressed air energy storage systems, constructing mechanistic models and data-driven models.

[0052] Furthermore, based on the principle of modular modeling, using the functional equipment of the compressed air energy storage system as the basic unit and the compressed air energy storage system as the object, a mechanistic model reflecting the static and dynamic characteristics of the object is constructed based on the mass, energy, and momentum conservation equations. Using historical data of the object's operation as a basis, with the object's state parameters as output and structural and typical excitation parameters as input, combined with the model results of the mechanistic model, a data-driven model of the system is constructed. The steps include:

[0053] S11: Modeling Preparation Stage. Determine the objectives of the compressed air energy storage system simulation, such as design, operation, maintenance, or troubleshooting; define the model object and scope, clarifying the basic components of the object under study and the operating conditions to be analyzed; and determine the input and output parameter sets of the model using functional equipment as the basic unit.

[0054] S12: Mechanism Modeling Stage. Starting from the research objectives, in order to simplify the model structure and reduce computational complexity, reasonable simplification assumptions need to be determined for the model; using the various functional devices of CAES as basic units, based on relevant theories, the conservation equations based on mass, energy, and momentum equations and the physical property equations of the working fluid are determined; the model structure of the compressed air energy storage system is determined; and the model parameters of the compressed air energy storage system are determined.

[0055] S13: Data-Driven Modeling Stage. Taking each functional device as the basic object, and based on the research objectives, determine the data-driven model structure that represents the input-output mapping relationship of the object; determine the data-driven model learning method according to the model structure and data characteristics; and learn the relevant parameters of the data-driven model through a large amount of actual working condition operation data.

[0056] S2: Model correction of compressed air energy storage system based on identification methods and deep learning algorithms;

[0057] Furthermore, the system acquires a set of operational parameters representing the working state of the object online or offline, and uses these parameters to determine the computational accuracy of the mechanistic model and the data-driven model. When the model error exceeds a predetermined threshold (defined based on research objectives and data accuracy requirements), the model is promptly corrected using identification methods and deep learning algorithms from artificial neural networks. The steps include:

[0058] Acquire operational data from the compressed air energy storage system;

[0059] Determine whether the error of the mechanism model is greater than the set threshold;

[0060] If the error exceeds the set threshold, perform online identification of mechanism model parameters and update the mechanism model; otherwise, return to obtain the compressed air energy storage system operation data.

[0061] Determine whether the error of the data-driven model exceeds the set threshold;

[0062] If the error exceeds the set threshold, perform data-driven model training and updates; otherwise, return to continue acquiring compressed air energy storage system operation data.

[0063] By using actual operating data of compressed air energy storage systems to complete the correction of mechanistic models and data-driven models, it can be ensured that the models can accurately characterize the static and dynamic characteristics of the objects.

[0064] Furthermore, the operating data of the compressed air energy storage system includes:

[0065] System-wide operating status parameter data;

[0066] Energy and mass transfer and conversion performance data of each device in the system;

[0067] Performance data for the entire system.

[0068] S3: Simulation, to complete the optimal scheduling of the compressed air energy storage system model.

[0069] Furthermore, the model's time and space complexity are evaluated in real time based on the simulation task, and the current computing power is assessed in real time. Combining the current computational accuracy of the mechanism model and the data-driven model, the model's optimization scheduling is completed in real time, so as to fully save the cost of simulation analysis of compressed air energy storage systems and improve its accuracy and speed.

[0070] Furthermore, the steps for scheduling a compressed air energy storage system model are as follows:

[0071] Define the simulation task for the compressed air energy storage system;

[0072] The system calculates the storage space and computing power requirements of simulation tasks based on data-driven and mechanistic models online, and compares them with the currently available computing resources to determine whether the computing resources meet the needs of the simulation tasks. The system also determines the accuracy of the mechanistic and data-driven models by comparing the actual measured data with the model calculation data.

[0073] Determine whether the accuracy of the data-driven model is higher than that of the mechanistic model;

[0074] If so, then select the simulation data-driven model for simulation;

[0075] If not, determine whether the computing power meets the computational requirements of the mechanism model. If it does, select the mechanism model for simulation; otherwise, select the data-driven model for simulation.

[0076] Online evaluation of the computational accuracy and complexity of the model, as well as the current computing power, enables online optimization and scheduling of mechanistic and data-driven models, thereby improving the performance of digital simulation.

[0077] Computer equipment can be a server, and its internal structure diagram can be as follows: Figure 4 As shown, the computer device includes a processor, memory, input / output (I / O) interfaces, and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is also connected to the system bus via the I / O interfaces. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides the environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The database stores data cluster data for the compressed air energy storage system. The I / O interfaces are used for information exchange between the processor and external devices. The communication interface is used for communication with external terminals via a network connection. When the computer program is executed by the processor, it implements a simulation method for a compressed air energy storage system based on mechanism and data fusion.

[0078] Example 2

[0079] like Figure 5 and 6 As an embodiment of the present invention, a simulation method for compressed air energy storage system based on mechanism and data fusion is provided. In order to verify the beneficial effects of the present invention, a scientific demonstration is carried out through simulation comparison test.

[0080] First, the method described in the above embodiments is applied to the optimization of control system parameters and compared with the traditional mechanism model.

[0081] Analyze the performance of the CAES control system under varying load conditions, and then optimize the control system parameters to improve the system's performance.

[0082] S1: Based on the research objectives and actual operational data, set the initial state parameter values ​​of the model using these as the objectives;

[0083] Typical measured data are shown in Table 1.

[0084] Table 1 Measured Data

[0085]

[0086] S2: Define the range and mechanism of change of control system parameters (including proportional, integral, derivative, and feedforward coefficients of the controller) to drive the optimization of control system parameters; the dynamic structure diagram of the speed regulation system during the stroke process is shown below. Figure 6 As shown in the table below:

[0087] Table 2 Expander speed regulator parameter settings

[0088]

[0089] S3: Run the model until a stable operating state is reached, that is, the absolute value of the derivative of all state variables with respect to time is less than a predetermined threshold (such as 1.0E-5).

[0090] Table 3 Steady-state data calculated by the model

[0091]

[0092] S4: After the model reaches steady state, ensure the normal operation of the control system to be optimized. Break the equilibrium state through typical disturbances (step or ramp disturbances), and record the changes in the system's state parameters over time until a new equilibrium condition is reached; the response curve is as follows. Figure 7 As shown.

[0093] S5: Based on the analysis of the change process of the corresponding controlled parameter value during the control process, calculate the corresponding control effect (such as overshoot, settling time, and steady-state accuracy).

[0094] S6: If the control effect does not meet the requirements, adjust the parameter size within the predetermined range according to the control parameter change mechanism set in S2, and return to S3 to continue the test until the requirements are met.

[0095] In this embodiment, after repeated runs and adjustments of the model, the optimal speed regulation scheme was determined, and the key parameters were... K p , K , T i The values ​​were set to 0.01, 0.1, and 100 seconds respectively. At these times, the expansion generator speed rise was the most stable, and the start-up time was the shortest.

[0096] The final simulation results are as follows:

[0097] The synergy between the mechanistic model and the data-driven model significantly alleviates the conflict between model complexity and computational cost. Furthermore, the self-evolutionary model approach effectively ensures the model's ability to continuously and accurately characterize the object. Compared to traditional mechanistic model methods, the computational accuracy is improved by more than 10%, while significantly reducing computational cost.

[0098] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments described above. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0099] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. A simulation method for compressed air energy storage systems based on mechanism and data fusion, characterized in that, include: Modeling of compressed air energy storage systems, constructing mechanistic models and data-driven models; Model correction of compressed air energy storage system based on identification methods and deep learning algorithms; Simulation was used to optimize the scheduling of the compressed air energy storage system model. The modeling of the compressed air energy storage system includes a modeling preparation stage, a mechanism modeling stage, and a data-driven modeling stage. The steps for correcting the compressed air energy storage system model are as follows: Acquire operational data from the compressed air energy storage system; Determine whether the error of the mechanism model is greater than the set threshold; If the error exceeds the set threshold, perform online identification of mechanism model parameters and update the mechanism model; otherwise, return to obtain the compressed air energy storage system operation data. Determine whether the error of the data-driven model exceeds the set threshold; If the error exceeds the set threshold, perform data-driven model training and updates; otherwise, return to continue acquiring compressed air energy storage system operation data. The steps for scheduling the compressed air energy storage system model are as follows: Define the simulation task for the compressed air energy storage system; The system calculates the storage space and computing power requirements of simulation tasks based on data-driven and mechanistic models online, and compares them with the currently available computing resources to determine whether the computing resources meet the needs of the simulation tasks. The accuracy of the mechanistic model and the data-driven model is determined by comparing the field measured data with the model calculation data. Determine whether the accuracy of the data-driven model is higher than that of the mechanistic model; If so, then select the simulation data-driven model for simulation; If not, then determine whether the computing power meets the computational requirements of the mechanism model; If the conditions are met, the mechanistic model is selected for simulation; otherwise, the data-driven model is selected for simulation.

2. The simulation method for compressed air energy storage systems based on mechanism and data fusion as described in claim 1, characterized in that: The steps in the modeling preparation stage include: determining the target of the compressed air energy storage system simulation for design, operation, maintenance, or fault handling; defining the model object and scope, clarifying the basic components of the object to be studied, the operating condition range to be analyzed, etc.; and determining the input and output parameter set of the model using functional equipment as the basic unit.

3. The simulation method for compressed air energy storage systems based on mechanism and data fusion as described in claim 2, characterized in that: The steps in the mechanism modeling stage include: starting from the research objectives, in order to simplify the model structure and reduce the computational complexity, reasonable simplification assumptions need to be determined for the model; taking each functional device of CAES as the basic unit, based on relevant theories, the conservation equations based on mass, energy, and momentum equations and the physical property equations of the working fluid are determined; the compressed air energy storage system model structure is determined; and the compressed air energy storage system model parameters are determined.

4. The simulation method for compressed air energy storage systems based on mechanism and data fusion as described in claim 3, characterized in that: The steps of the data-driven modeling stage include: taking each functional device as the basic object, determining the data-driven model structure that represents the input-output mapping relationship of the object based on the research objective; determining the data-driven model learning method according to the model structure and data characteristics; and learning the relevant parameters of the data-driven model through a large amount of actual working condition operation data.

5. The simulation method for compressed air energy storage systems based on mechanism and data fusion as described in claim 4, characterized in that: The operating data of the compressed air energy storage system includes: System-wide operating status parameter data; Energy and mass transfer and conversion performance data of each device in the system; Performance data for the entire system.

6. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 5.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 5.

Images