Digital Twin Modeling Method, Device, Equipment and Medium for Generator Set

Abstract

The present application discloses a digital twin modeling method, device, equipment and medium for a generator set, which relates to the field of computer technology. The generator set includes a boiler system, a steam turbine system and a molten salt system. The method includes: obtaining the structural relationship between the boiler system, the steam turbine system and the molten salt system; dividing the structural domain of the generator set according to the structural relationship to obtain a plurality of sub-structures; determining the operating principles corresponding to the plurality of sub-structures under various working conditions; and performing digital twin modeling on the dominant thermodynamics dynamic characteristics of the generator set according to the operating principles corresponding to the plurality of sub-structures under various working conditions. It can be seen that in this method, the molten salt system is introduced for digital twin modeling, and the structural domain of the new generator set is divided and combined with the operating principles under various working conditions, so that the model after digital twin modeling can be closer to the actual situation of the generator set and improve the accuracy of the model.

Description

Technical Field

[0001] This application relates to the field of computer technology, and in particular, to a digital twin modeling method, device, equipment and medium for a generator set. Background Art

[0002] For the digital transformation of thermal power units, most of the existing technologies adopt methods such as white-box mechanism modeling, black-box data modeling, and grey-box composite modeling to perform digital twin modeling on the power generation process of thermal power units.

[0003] Among them, white-box mechanism modeling deduces the mechanism model of a thermal power unit based on the energy balance equation, mass balance equation, working fluid characteristics, and constraint equations; black-box data modeling establishes the data model of a thermal power unit based on the operation data of thermal power generation and uses machine learning algorithms such as neural networks; grey-box composite modeling identifies the parameters of the mechanism model based on the mechanism model of thermal power generation and combines the operation data.

[0004] However, the above methods of white-box mechanism modeling, black-box data modeling, and grey-box composite modeling do not consider the molten salt system and cannot perform modeling and analysis on the unit with the coupling of a boiler and molten salt. Summary of the Invention

[0005] This application provides a digital twin modeling method, device, equipment and medium for a generator set, which can perform modeling and analysis on the unit with the coupling of a boiler, a steam turbine and molten salt.

[0006] To achieve the above object, this application adopts the following technical solutions:

[0007] In a first aspect, this application provides a digital twin modeling method for a generator set, the unit includes a boiler system, a steam turbine system and a molten salt system, and the method includes:

[0008] Obtain the structural relationship between the boiler system, the steam turbine system and the molten salt system;

[0009] According to the structural relationship, divide the unit in the structural domain to obtain a plurality of sub-structures;

[0010] Determine the operating principles corresponding to the plurality of sub-structures under various working conditions;

[0011] According to the operating principles corresponding to the plurality of sub-structures under various working conditions, perform digital twin modeling on the power generation characteristics of the unit.

[0012] Optionally, the boiler system includes a boiler, an economizer, a molten salt heat exchanger, a boiler reheater, a boiler superheater, a first valve, a first hydraulic / electric pump, a first pipeline, etc.; the steam turbine system includes high-pressure feedwater heaters, a deaerator, low-pressure feedwater heaters, a low-pressure cylinder, an intermediate-pressure cylinder, a high-pressure cylinder, a second valve, a second hydraulic / electric pump, a second pipeline, etc.; the molten salt system includes a molten salt superheater, a molten salt evaporator, a molten salt preheater, a high-temperature molten salt tank, a steam-molten salt heat exchanger, a low-temperature molten salt tank, a third valve, a third hydraulic / electric pump, a third pipeline, etc.

[0013] Optionally, according to the structural relationship, the unit is divided into structural domains to obtain multiple sub-structures, including:

[0014] According to the directed graph node relationship matrix corresponding to the structural relationship, the unit is divided into structural domains to obtain multiple sub-matrices, and the multiple sub-matrices are used to characterize the multiple sub-structures of the unit.

[0015] Optionally, according to the directed graph node relationship matrix corresponding to the structural relationship, the division of the structural domains of the unit includes:

[0016] Using the directed graph node clustering algorithm, the directed graph node relationship matrix corresponding to the structural relationship is processed to divide the structural domains of the unit.

[0017] Optionally, the method further includes:

[0018] Obtaining the actual operation data corresponding to the unit during the power generation process under the multiple working conditions;

[0019] According to the operating principles corresponding to the multiple sub-structures under multiple working conditions, the digital twin modeling of the power generation characteristics of the unit includes:

[0020] According to the operating principles corresponding to the multiple sub-structures under multiple working conditions and the actual operation data, for different task requirements, an algebraic or appropriately-ordered differential equation mechanism model, a data-driven machine learning agent model, and their multiple combinations are used to perform digital twin modeling on the power generation characteristics of the unit.

[0021] In a second aspect, the present application provides a digital twin modeling device for a new type of generator set. The unit includes a boiler system, a steam turbine system, and a molten salt system. The device includes:

[0022] An acquisition module, configured to acquire the structural relationship between the boiler system, the steam turbine system, and the molten salt system;

[0023] A division module, which divides the structural domains of the unit according to the structural relationship to obtain multiple sub-structures;

[0024] A determination module determines the operating principles corresponding to the multiple sub-structures under various working conditions.

[0025] A modeling module performs digital twin modeling on the power generation characteristics of the unit according to the operating principles corresponding to the multiple sub-structures under various working conditions.

[0026] Optionally, the boiler system includes a boiler, an economizer, a molten salt heat exchanger, a boiler reheater, a boiler superheater, a first valve, a first hydraulic / electric pump, a first pipeline, etc.; the steam turbine system includes high-pressure feed water heaters, a deaerator, low-pressure feed water heaters, a low-pressure cylinder, an intermediate-pressure cylinder, a high-pressure cylinder, a second valve, a second hydraulic / electric pump, a second pipeline, etc.; the molten salt system includes a molten salt superheater, a molten salt evaporator, a molten salt preheater, a high-temperature molten salt tank, a steam-molten salt heat exchanger, a low-temperature molten salt tank, a third valve, a third hydraulic / electric pump, a third pipeline, etc.

[0027] Optionally, the partitioning module is specifically configured to partition the structural domain of the unit according to the directed graph node relationship matrix corresponding to the structural relationship, obtaining a plurality of sub-matrices, and the plurality of sub-matrices are used to characterize the multiple sub-structures of the unit.

[0028] Optionally, the partitioning module is specifically configured to process the directed graph node relationship matrix corresponding to the structural relationship by using a directed graph node clustering algorithm to partition the structural domain of the unit.

[0029] Optionally, the acquisition module is further configured to acquire the actual operating data corresponding to the unit during the power generation process under the various working conditions.

[0030] The modeling module is specifically configured to perform digital twin modeling on the power generation characteristics of the unit according to the operating principles corresponding to the multiple sub-structures under various working conditions.

[0031] In a third aspect, the present application provides a computer-readable storage medium for storing a computer program, and the computer program is used to execute the method according to any one of the first aspect.

[0032] In a fourth aspect, the present application provides a computer program product having a computer program stored thereon, and when the program is executed by a processing device, the method according to any one of the first aspect is implemented.

[0033] As can be seen from the above technical content, the technical solution of the present application has the following beneficial effects:

[0034] The present application provides a digital twin modeling method for a generator set, wherein the unit includes a boiler system, a steam turbine system, and a molten salt system, and the method includes: obtaining the structural relationship between the boiler system, the steam turbine system, and the molten salt system; dividing the unit into structural domains according to the structural relationship to obtain multiple substructures; determining the corresponding operating principles of the multiple substructures under various working conditions; and performing digital twin modeling on the power generation characteristics of the unit according to the corresponding operating principles of the multiple substructures under various working conditions. It can be seen that in this method, a molten salt system is introduced for data modeling, and the unit is structurally divided into domains and combined with the operating principles of various working conditions, so that the model after digital twin modeling can be closer to the actual situation of the unit, thereby improving the accuracy of the model.

[0035] It should be understood that the description of technical features, technical solutions, beneficial effects or similar language in this application does not imply that all features and advantages can be realized in any single embodiment. On the contrary, it is understood that the description of a feature or beneficial effect means that a specific technical feature, technical solution or beneficial effect is included in at least one embodiment. Therefore, the description of a technical feature, technical solution or beneficial effect in this specification does not necessarily refer to the same embodiment. Furthermore, the technical features, technical solutions and beneficial effects described in the present embodiment can also be combined in any appropriate manner. Those skilled in the art will understand that the embodiment can be implemented without one or more specific technical features, technical solutions or beneficial effects of a specific embodiment. In other embodiments, additional technical features and beneficial effects can also be identified in specific embodiments that do not embody all embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] Figure 1 A schematic diagram of a thermal power unit provided in an embodiment of the present application;

[0037] Figure 2 A flowchart of a digital twin modeling method for a generator set provided in an embodiment of the present application;

[0038] Figure 3 A digital twin modeling principle diagram provided in an embodiment of the present application;

[0039] Figure 4 A schematic diagram of the software and hardware structure of a digital twin model provided in an embodiment of the present application;

[0040] Figure 5 A schematic diagram of a digital twin modeling device for a novel generator set provided in an embodiment of the present application. DETAILED DESCRIPTION

[0041] The terms "first", "second", "third", etc. in the description, claims and drawings of this application are used to distinguish different objects, rather than to limit a specific order.

[0042] In the embodiments of this application, words such as "exemplary" or "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design solution described as "exemplary" or "for example" in the embodiments of this application should not be construed as more preferred or more advantageous than other embodiments or design solutions. Rather, the use of words such as "exemplary" or "for example" is intended to present relevant concepts in a specific manner.

[0043] The cleanization of power sources is an important feature of the new power system, and the energy provided by the new power system will account for an increasingly large proportion of China's power supply. Due to the characteristics of new energy power generation operation, it has the disadvantages of poor stability and large impact on the power grid.

[0044] The demand for the reliability of the safe operation of the power grid is more urgent, which requires thermal power units with stable power supply to gradually transform into providers of frequency regulation, standby, and emergency capacity services. Improving the flexibility of thermal power units has become an important development direction for thermal power units.

[0045] Existing medium and small capacity units (300MW class, 600MW class) have been in operation for a long time, have low low-load efficiency, and relatively poor equipment performance. It is expected that through flexibility transformation, they will become the main units for load regulation and provide power support for the power grid; large-capacity 1000MW class coal-fired units have high efficiency and good equipment performance, and can operate at high loads to provide power support for the power grid.

[0046] The embodiments of this application provide a new type of thermal power unit, as Figure 1 shown. This figure is a schematic diagram of a thermal power unit provided by the embodiments of this application. The thermal power unit includes: boiler 101, economizer 102, molten salt heat exchanger 103, boiler reheater 104, boiler superheater 105, high-pressure feedwater heater 106, deaerator 107, low-pressure feedwater heater 108, low-pressure cylinder 109, intermediate-pressure cylinder 110, high-pressure cylinder 111, molten salt superheater 112, molten salt evaporator 113, molten salt preheater 114, high-temperature molten salt tank 115, steam-molten salt heat exchanger 116, low-temperature molten salt tank 117.

[0047] The steam from the high-pressure cylinder 111 of the steam turbine is used to heat the molten salt from the low-temperature molten salt storage tank 117 through the steam-molten salt heat exchanger 116 to achieve heat storage.

[0048] The circulating water from the high-pressure heater 106 passes through the molten salt preheater 114, the molten salt evaporator 113, and the molten salt superheater 112 in sequence, exchanges heat with the high-temperature molten salt, obtains high-temperature and high-pressure steam that meets certain conditions, and is injected into the middle part of the high-pressure cylinder 111 of the steam turbine to do work.

[0049] Part of the steam after doing work in the high-pressure cylinder 111 of the steam turbine can be reheated by the molten salt reheater and then injected into the middle part of the intermediate-pressure cylinder 110 of the steam turbine to do work, realizing the heat release of the molten salt heat storage and generating steam to increase the load of the steam turbine.

[0050] When the unit reduces the load, the main steam and furnace flue gas of the boiler are extracted regularly; if the main steam A2 is extracted, the low-temperature molten salt in the low-temperature molten salt tank 117 is heated by the molten salt superheater 112, and the steam B2 at the outlet of the molten salt superheater 112 enters the intermediate-pressure cylinder 110 to do work after passing through the furnace reheater; if the furnace flue gas is extracted, the low-temperature molten salt in the low-temperature molten salt tank 117 is heated by the molten salt heat exchanger 103 at the tail of the furnace.

[0051] When the unit increases the load, the high-temperature molten salt tank 115 releases heat through the molten salt superheater 112, the molten salt evaporator 113, and the molten salt preheater 114 in sequence. The branch of the feed water of the high-pressure heater 106 passes through the molten salt preheater 114, the molten salt evaporator 113, and the molten salt superheater 112 in sequence, generates main steam and enters the high-pressure cylinder 111 to do work.

[0052] Currently, there are various modeling methods, such as white-box mechanism modeling, black-box data modeling, and gray-box composite modeling. Among them, for white-box mechanism modeling, the model complexity is high, the model parameter identification is difficult, the model characteristics are inconsistent with the actual situation, and it is mostly used for fine simulation or training of the thermal power generation process; for black-box data modeling, only the input-output external characteristics are considered, the internal mechanism characteristics are unknown, it depends on the modeling data and algorithms and needs to be updated and maintained, and the number of data models is large, and it is mostly used for the state monitoring and operation and maintenance of the thermal power generation process; for gray-box composite modeling, it is generally only applicable to linear system modeling, the model order is low, and the approximation performance for the complex nonlinearity of the full operating conditions is limited, resulting in a deviation between the optimal approximation characteristics of the model and the actual characteristics. At the same time, the model parameter identification is difficult, and it is mostly used for the controller design of the thermal power generation process. It can be seen that the existing modeling methods only model the thermal power generating unit and do not perform digital twin modeling for the unit coupled with the molten salt system.

[0053] In view of this, an embodiment of the present application provides a digital twin modeling method for a generator set. The generator set targeted by this digital twin modeling method includes a boiler system and a molten salt system. Specifically, the method includes: obtaining the structural relationship between the boiler system and the molten salt system, then dividing the structural domain of the generator set according to this structural relationship to obtain multiple sub-structures, then determining the operating principles corresponding to the multiple sub-structures under various working conditions, and finally performing digital twin modeling on the dominant thermodynamic dynamic characteristics of the generator set based on the operating principles corresponding to the multiple sub-structures under various working conditions. In this method, the molten salt system is introduced for data modeling, and the structural domain of the generator set is divided and combined with the operating principles under various working conditions, so that the model after digital twin modeling can be closer to the actual situation of the generator set and improve the accuracy of the model.

[0054] For ease of understanding, the digital twin modeling method for the generator set provided by the embodiment of the present application will be introduced below with reference to the accompanying drawings.

[0055] As Figure 2 shown, this figure is a flowchart of a digital twin modeling method for a generator set provided by an embodiment of the present application. The generator set includes a boiler system, a steam turbine system, and a molten salt system. In some examples, the generator set can be as described above Figure 1 shown, the method includes:

[0056] S201: Obtain the structural relationship between the boiler system, the steam turbine system, and the molten salt system.

[0057] The boiler system may include Figure 1 the boiler 101, economizer 102, molten salt heat exchanger 103, boiler reheater 104, and boiler superheater 105 in Figure 1 ; the steam turbine system may include Figure 1 the high-pressure feedwater heater 106, deaerator 107, low-pressure feedwater heater 108, low-pressure cylinder 109, intermediate-pressure cylinder 110, and high-pressure cylinder 111 in

[0058] ; the molten salt system may include

[0059] the molten salt superheater 112, molten salt evaporator 113, molten salt preheater 114, high-temperature molten salt tank 115, steam-molten salt heat exchanger 116, and low-temperature molten salt tank 117 in

[0060] In some examples, after determining the structural relationship of the above generator set, the structural domain of the generator set can be divided to obtain multiple sub-structures. Among them,Figure 1 The components shown in

[0061] It should be noted that the above sub-structures are only introduced exemplarily. Those skilled in the art can divide the unit into structural domains based on actual needs to obtain different sub-structures.

[0062] In some embodiments, based on the above structural relationship, a corresponding directed graph node relationship matrix can be determined. Then, based on the directed graph node relationship matrix, the unit can be divided into structural domains to obtain multiple sub-matrices, and the multiple sub-matrices are used to represent the multiple sub-structures of the unit, that is, one sub-matrix represents one sub-structure.

[0063] Among them, a structural domain division for node clustering based on the directed graph of the function-physics combined boiler system-molten salt system coupling unit can be established, and multiple sub-matrices can be obtained based on the directed graph node relationship matrix. In some examples, based on the boiler system, the molten salt system, and their coupling mechanism, a directed graph G=(V, W) of the boiler-molten salt coupling unit can be obtained by establishing the functional and physical connection relationships between each subsystem (or equipment) under various load conditions using directed graph nodes. Among them, the node vector V represents the subsystem (or equipment), including but not limited to boilers, economizers, molten salt heat exchangers, boiler reheaters, boiler superheaters, high-pressure feedwater heaters, deaerators, low-pressure feedwater heaters, low-pressure cylinders, intermediate-pressure cylinders, high-pressure cylinders, molten salt superheaters, molten salt evaporators, molten salt preheaters, high-temperature molten salt tanks, steam-molten salt heat exchangers, low-temperature molten salt tanks, valves, hydraulic / electric pumps, pipelines, etc. Initially, based on the operating principle of the unit and prior knowledge, each node vector V=[V1, V2, …, V i ,…,V n can be set. The directed graph relationship matrix W represents the connection relationships between each node (for example, when there is a connection relationship under the operating condition, the value is 1, and when there is no connection relationship, the value is 0), and there is:

[0064]

[0065] Among them, W ij =W ji , representing the connection relationship between nodes i and j.

[0066] In some examples, a directed graph node clustering algorithm can be used to process the directed graph node relationship matrix corresponding to the structural relationship, so as to divide the structural domain of the unit. Among them, the directed graph node clustering algorithm includes but is not limited to the Louvain algorithm and the Tarjan algorithm. For example, the directed graph node clustering algorithm is used to cluster different subsystems, and each cluster can be called a structural domain (or sub-structure) D p (p = 1, 2, …, m; m is the number of structural domains divided by the coupled power generation system, that is, how many sub-structures).

[0067] The initial structural domain division can be determined according to the operating principle of the unit and prior knowledge. After multiple iterations, a structural domain division knowledge base can be constructed for coupled power generation systems of different types (including but not limited to natural circulation boilers, supercritical / ultra-supercritical once-through boilers, etc.) and different capacity levels (including but not limited to 300 MW, 350 MW, 600 MW, etc.). Subsequently, based on the structural domain division knowledge base for structural domain division, the efficiency of structural domain division can be improved.

[0068] In some examples, each structural domain represents a subsystem or device with functional or physical connection relationships with each other under full operating conditions of the coupled power generation system, which can reflect the rationality of modeling according to this structural domain. Based on the structural domain division result obtained by Louvain directed graph clustering, the initial structural domain division can be determined according to the operating principle of the unit and prior knowledge. After multiple iterations, a structural domain division knowledge base can be constructed for a 350MW supercritical once-through boiler coal-fired thermal power unit - high-temperature molten salt thermal energy storage coupled flexible power generation system. Subsequently, based on the structural domain division knowledge base for structural domain division, the efficiency of structural domain division can be improved.

[0069] For example, for a 350MW supercritical once-through boiler coal-fired thermal power unit - high-temperature molten salt thermal energy storage coupled flexible power generation system, the once-through boiler unit (i.e., the boiler system) is divided into three major structural domains: the coal pulverizing system, the boiler steam-water system, and the steam turbine system. The high-temperature molten salt thermal energy storage system (i.e., the molten salt system) is divided into structural domains such as the high-temperature molten salt tank, the low-temperature molten salt tank, the furnace flue gas - molten salt heat exchanger and the molten salt transportation pipeline system, the high-temperature molten salt - steam-water system, and the low-temperature molten salt - superheated steam heat exchanger and the molten salt transportation pipeline system.

[0070] S203: Determine the operating principles corresponding to multiple sub-structures under various working conditions.

[0071] In some examples, model derivation can be carried out based on the parameters of subsystems or devices included in the substructure. For example, for subsystems or devices with a mature mechanism modeling foundation (including but not limited to coal pulverizing systems, boiler feedwater and steam systems, steam turbine systems, high / low temperature molten salt thermal energy storage systems, molten salt thermal energy storage feedwater and steam systems, water supply or steam pipelines, etc.), a white-box mechanism model of an appropriate order can be adopted. For subsystems or devices that are complex and nonlinear and do not have a mature mechanism modeling foundation (including but not limited to furnace combustion systems), a black-box parameter model can be adopted (for example, dynamic or static parameter models such as autoregressive with exogenous input (ARX) models, subspace identification models, partial least squares linear regression models, Logistic regression models, piecewise affine PWA models, piecewise affine autoregressive with exogenous input PWARX models, etc.). According to the functional and physical connection relationships between different subsystems or devices, white-box mechanism models and black-box parameter models are connected in ways such as multi-stage series, multi-stage parallel, or multi-stage hybrid series / parallel. On this basis, multi-scale dynamic integration derivation of the models of different subsystems or devices is carried out to obtain the modular integrated parameter models corresponding to each domain.

[0072] In some examples, the mechanism parameter model of the coal pulverizing system is as follows:

[0073]

[0074] Where, u B is the fuel quantity command, with the unit of kg / s; r B ′ is the actual coal quantity entering the mill, with the unit of kg / s; τ is the delay time, with the unit of s; r B is the pulverized coal quantity entering the boiler, with the unit of kg / s; M coal is the coal storage quantity in the mill, with the unit of kg; c B is the basic output coefficient of the mill; f H is the coal grindability correction coefficient; f W is the coal moisture correction coefficient; f R is the pulverized coal fineness correction coefficient.

[0075] The mechanism parameter model of the boiler feedwater and steam system is as follows:

[0076]

[0077] Where, is the average point working medium density of the heating section, with the unit of kg / m 3 ; D fw is the feedwater flow rate, with the unit of kg / s; D s is the steam flow rate at the outlet of the superheater, with the unit of kg / s; v t is the total internal volume of the economizer, water wall, and steam separator, with the unit of m 3 ; is the average point working fluid internal energy of the heated section, with the unit of kJ / kg; h fw is the feed water enthalpy value, with the unit of kJ / kg; h s is the specific enthalpy of the steam at the outlet of the superheater, with the unit of kJ / kg, h s = u s + p s / ρ s ; k0 is the heat absorption gain of the heated section, with the unit of kJ / kg; p m is the steam pressure at the steam-water separator, with the unit of MPa; p s is the steam pressure at the outlet of the superheater, with the unit of MPa; σ is the resistance coefficient of the superheater pipeline; D sw is the total equivalent desuperheating water flow rate, with the unit of kg / s; D sw = D1G2G3G4 + D2G3G4 + D3G4, where D1, D2, and D3 represent the flow rates of the first-stage, second-stage, and third-stage desuperheating water respectively, with the unit of kg / s, and G2, G3, and G4 represent the mathematical models of the second-stage, third-stage, and final-stage superheaters; D st is the steam flow rate at the turbine inlet, i.e., the main steam flow rate, with the unit of kg / s; h st is the specific enthalpy of the steam at the turbine inlet, i.e., the main steam specific enthalpy, with the unit of kJ / kg; p s = p st , p st is the steam pressure at the turbine inlet, i.e., the main steam pressure, with the unit of MPa; s1, s2 are dynamic parameters; ρ m is the steam density at the steam-water separator, with the unit of kg / m 3 ; u m is the steam internal energy at the steam-water separator, with the unit of kJ / kg; Q0 is the heat absorbed by the steam flowing through the superheater pipeline, with the unit of kJ; Δp is the differential pressure generated by the steam flowing through the superheater pipeline, Δp = p m - p st , with the unit of MPa; z1, z2 are coefficients related to pipeline resistance and gas specific heat; D m0 is the initial mass flow rate of the steam; v0 is the specific volume of the steam, which is related to the steam pressure and temperature, and g(·) is a function with p m as the independent variable.

[0078] The mechanism parameter model of the steam turbine system is as follows:

[0079]

[0080] Among them, ρ st is the steam density at the turbine inlet, with the unit of kg / m 3 ; u t is the opening degree of the steam turbine control valve, which can be characterized by a percentage; λ, α are coefficients; N eThe unit of the unit load is MW; k2 is the gain of the steam turbine.

[0081] In some examples, for a high-temperature molten salt thermal energy storage system (such as 5KW), it is divided into structural domains such as a high-temperature molten salt tank, a low-temperature molten salt tank, a furnace flue gas - molten salt heat exchanger, a molten salt transportation pipeline system, a high-temperature molten salt - steam-water system, a low-temperature molten salt - superheated steam heat exchanger, and a molten salt transportation pipeline system, and a simplified low-order white-box mechanism parameter model is adopted for all of them.

[0082] Among them, the high-temperature molten salt tank and the low-temperature molten salt tank have the same model structure. For example, the mechanism parameter model of the molten salt tank is as follows:

[0083]

[0084] Among them, m salt,in is the mass flow rate at the inlet of the molten salt thermal energy storage tank, with the unit of kg / s; T salt,in is the molten salt temperature at the inlet of the molten salt thermal energy storage tank, with the unit of °C; T salt,tank is the temperature of the molten salt thermal energy storage tank, with the unit of °C; Δt is the micro-element time period, with the unit of s; M salt,tank is the initial mass of the molten salt thermal energy storage tank, with the unit of kg.

[0085] The high-temperature molten salt - steam-water system includes a preheater, an evaporator, and a superheater. The mechanism parameter model of the high-temperature molten salt - steam-water system is as follows:

[0086]

[0087] Among them, c salt is the specific heat capacity at constant pressure of the molten salt, with the unit of kJ / (kg·°C); h eva,in is the enthalpy value of the molten salt entering the evaporator, with the unit of kJ / kg; h eva,out is the enthalpy value of the molten salt at the outlet of the evaporator, with the unit of kJ / kg; m salt,eva is the mass flow rate of the molten salt in the evaporator, with the unit of kg / s; M salt,eva is the mass of the molten salt in the evaporator, with the unit of kg; Q salt,eva is the heat transferred from the molten salt to the pipe wall, with the unit of kJ; T salt,eva is the temperature of the molten salt in the evaporator, with the unit of °C.

[0088] c pipe is the specific heat capacity of the evaporator pipe, with the unit of kJ / (kg·°C); M pipe,eva is the mass of the pipe in the evaporator, with the unit of kg; T pipe,eva is the temperature of the inner wall of the evaporator pipe, with the unit of °C; Q s,eva is the heat transfer amount from the molten salt in the evaporator to the inner wall of the pipe, with the unit of J; Q w,eva is the heat transfer amount from the outer wall of the evaporator pipe to the water side outside the pipe, with the unit of J; Ai,eva , A o,eva are the areas of the inner and outer pipe walls respectively, with the unit of m 2 ; T w,eva is the water-side temperature of the outer wall of the evaporator pipe, with the unit of °C; U i,eva , U o,eva are the convective heat transfer coefficients between the molten salt in the evaporator and the inner pipe wall, and between the outer pipe wall and the outer water respectively, with the unit of W / m 2 ·K.

[0089] M w,eva is the mass of water in the evaporator, with the unit of kg; m fw,eva is the mass flow rate of the feed water in the evaporator, with the unit of kg / s; m cond,eva is the mass flow rate of the part of the steam in the evaporator cooled by the feed water entering the evaporator, with the unit of kg / s; m zq,eva is the evaporation rate of the steam in the evaporator, with the unit of kg / s; m d,eva is the mass flow rate of the blowdown water, with the unit of kg / s.

[0090] M zq,eva is the mass of the steam in the evaporator, with the unit of kg; m zq,eva,o is the steam flow rate at the outlet of the evaporator, with the unit of kg / s; h fw,eva is the enthalpy value of the feed water in the evaporator, with the unit of kJ / kg; h zq,eva is the enthalpy value of the steam in the evaporator, with the unit of kJ / kg; V v,eva , V w,eva are the volumes of the steam and water in the evaporator respectively, with the unit of m 3 ; ρ v,eva , ρ w,eva are the densities of the steam and water in the evaporator respectively, with the unit of kg / m 3 .

[0091] h w,eva is the enthalpy value of the water in the evaporator, with the unit of kJ / kg; P d is the continuous blowdown rate, which can be characterized by a percentage.

[0092] P w,eva is the water-side pressure in the evaporator, with the unit of MPa; P w,sup is the water-side pressure in the superheater, with the unit of MPa; ξ eva is the admittance coefficient of the evaporator, which is related to the valve characteristics, with the unit of Pa·s 2 / kg 2 .

[0093] The mechanism parameter model of the low-temperature molten salt-superheated steam heat exchanger is as follows:

[0094]

[0095] Among them, V zq,sup is the steam volume in the superheater, with the unit of m 3 ; m zq,sup,i , m zq,sup,o are the mass flow rates of the steam entering and leaving the superheater, with the unit of kg / s; ρ zq,sup,i , ρ zq,sup,o are the densities of the steam entering and leaving the superheater, with the unit of kg / m 3 .

[0096] h zq,sup,i , h zq,sup,o are the enthalpy values of the steam entering and leaving the superheater, with the unit of kJ / kg; Q zq,sup is the heat absorbed by the steam in the superheater from the pipeline heating, with the unit of kJ.

[0097] ξ sup is the flow resistance or linear admittance of the steam in the superheater, with the unit of Pa·s 2 / kg 2 ; P zq,sup,i is the inlet pressure of the steam in the superheater, with the unit of MPa; P zq,sup is the steam pressure in the superheater, with the unit of MPa.

[0098] c salt is the constant-pressure specific heat capacity of the molten salt, with the unit of kJ / (kg·℃); M salt,sup is the mass of the molten salt flowing through the superheater, with the unit of kg; T salt,sup is the temperature of the molten salt flowing through the superheater, with the unit of ℃; m salt,sup is the mass flow rate of the molten salt flowing through the superheater, with the unit of kg / s; Q salt,sup is the heat released by the molten salt in the superheater to the pipe wall, with the unit of kJ.

[0099] The furnace flue gas - molten salt heat exchanger can adopt the mechanism parameter model structure of the above-mentioned low-temperature molten salt - superheated steam heat exchanger, which will not be elaborated here.

[0100] In some examples, the molten salt transport pipeline system adopts a modeling method that uses the lumped parameter model of multiple sections of pipelines in series to approximate long-distance pipelines. Among them, the mechanism parameter model of a single section of pipeline is as follows:

[0101]

[0102] Among them, C salt,pipe is the heat capacity of the molten salt in a single section of pipeline, with the unit of J / ℃; T salt,pipe,in , T salt,pipe,out are the input and output temperatures of the molten salt in a single section of pipeline, with the unit of ℃; T am,pipe is the ambient temperature of the pipeline, with the unit of ℃; csalt is the specific heat capacity of the molten salt, with the unit of kJ / (kg·℃); α salt,pipe is the convective heat transfer coefficient between the water flow in the pipeline and the environment (J / (m 2 ·℃·s)); Q salt,pipe is the mass flow rate of the molten salt in the pipeline, with the unit of kg / s; S salt,pipe is the heat transfer area of the pipeline, with the unit of m 2 .

[0103] The pulverizing system, boiler steam-water system, steam turbine system and other sub-structures of the boiler system, as well as the modular mechanism parameter modeling of the high-temperature molten salt tank, low-temperature molten salt tank, furnace flue gas-molten salt heat exchanger and molten salt transportation pipeline system, high-temperature molten salt-steam-water system, low-temperature molten salt-superheated steam heat exchanger, molten salt transportation pipeline system and other sub-structures of the molten salt system have been introduced above respectively.

[0104] In addition to the mechanism parameter model, if there are structural domains with complex non-linear characteristics that are difficult to model, a black-box parameterization model (including but not limited to autoregressive ARX model, piecewise affine PWA model, piecewise affine autoregressive PWARX model, subspace identification model, Logistic regression model, etc.) can be used to replace the above mechanism parameter model.

[0105] Based on the lumped parameter modeling theory, the low-order mechanism parameter models of different structural domains adopted are linear or non-linear differential equations, and then the modular integrated parameter models L p (p = 1, 2, …, m; m is the number of structural domains divided by the combined power generation system, that is, the number of sub-structures) can be uniformly expressed by the following structure:

[0106]

[0107] Among them, A, B, C, and D are linear or non-linear matrices of appropriate dimensions; k is the timing index of the measured signal under the sampling period T; y(k) can be a single output variable or a multi-output vector.

[0108] It can be seen that through the above model, the operating principles corresponding to multiple sub-structures can be characterized.

[0109] In some examples, the differential dynamic regression vector R(k) = [y p corresponding to the integrated parameter model L p of the sub-structure D can also be extracted to characterize the operating characteristics of D p under all operating conditions, where R(k) = [y T (k - 1), y T (k - 2), … y T (k - n a ), u T (k - 1), uT (k - 2),…, u T (k - n b )] T , where n a and n b are the delay orders of the system output and input respectively. A convex partition is performed on the high - dimensional non - linear operating space spanned by R(k), and then the operating principles corresponding to the sub - structures under various working conditions can be obtained. Then, based on a similar method, the operating principles of each sub - structure under various working conditions can be obtained.

[0110] Among them, various methods can be used for convex partitioning, including but not limited to methods such as direct high - dimensional clustering partitioning of R(k) regression vectors, extraction of R(k) regression vectors and their high - dimensional clustering partitioning, and clustering partitioning of R(k) regression matrices for a specific duration. For the high - dimensional clustering results, methods such as hyperplane partitioning (including but not limited to support vector machines, soft - margin support vector machines, etc.) can be used to obtain hyperplane equations that can represent the boundaries of different sub - operating domains. Based on the regression vector R(k) and the hyperplane equations, the operating domain of the coupled power generation system at time k can be determined. Finally, for the integrated parameter model L p corresponding to the sub - structure D p,l (l = 1, 2,…, S p ), S p sub - operating domains are obtained, that is, the operating principles corresponding to the sub - structures under various working conditions are obtained.

[0111] S204: Digital twin modeling of the power generation characteristics of the new type of unit according to the operating principles corresponding to multiple sub - structures under various working conditions.

[0112] When performing digital twin modeling, one or a combination of algebraic or differential equation mechanism models and data - driven machine learning proxy models can be used for modeling.

[0113] In some examples, after determining the operating principles corresponding to the sub - structures under various working conditions, digital twin modeling of the dominant thermodynamic dynamic characteristics of the new type of unit power generation can be performed.

[0114] In other embodiments, the real - time operating data corresponding to the new type of unit power generation under various working conditions can also be obtained, and then based on the operating principles corresponding to multiple sub - structures under various working conditions and the real - time operating data, digital twin modeling of the dominant thermodynamic dynamic characteristics of the new type of unit power generation can be performed.

[0115] The hybrid semi - parametric modeling of the boiler system and the molten salt system mainly includes parameter identification of the model L p,l based on each sub - operating domain and deviation dynamic neural network compensation modeling of the state - space equation based on machine learning.

[0116] In some examples, taking the regression vector R(k) as the input and y(k) as the output, numerical methods (including but not limited to equation error parameter identification, gradient correction parameter identification, probability density approximation parameter identification, least squares identification, etc.) or heuristic intelligent optimization methods (including but not limited to genetic algorithms, particle swarm algorithms, simulated annealing algorithms) are used to obtain the linear or nonlinear model L in the l-th operating region p,l parameters and establish the models of each sub-operating region.

[0117] For example, define ( is the model output value), the deviation compensation regression vector R e (k) = [e T (k - 1), e T (k - 2), …, e T (k - n e ), y T (k - 1), y T (k - 2), …, y T (k - n a ), u T (k - 1), u T (k - 2), …, u T (k - n b )] T (n e is the autoregressive order of e(k)). Taking R e (k) as the input and e(k) as the output, a machine learning algorithm (including but not limited to deep neural network machine learning methods such as recurrent neural networks, autoencoder-recurrent neural networks, etc.) is used to establish a multi-input-multi-output deviation dynamic compensation model of e y (k), which can achieve unified compensation for all S p [[ID= forty-seven]]th operating region models in the p-th structural domain. If it is necessary to focus on the measurable state x ob , x ob can be used as the output, and the deviation dynamic compensation of the measurable state can be realized in e y (k) and fed back to the state equation x(k + 1); the deviation compensation term of the unmeasurable state is set to 0, and the deviation dynamic compensation term e y (k) of the measurable state x ob fed back from e xob (k) is introduced to form the deviation dynamic compensation term e x (k) of the state equation.

[0118]

[0119] where l = 1, 2, …, S p。

[0120] Then, for the l-th running domain of the p-th domain, the sub-running domain models L with deviation dynamic compensation are obtained p,l,DC , which has the ability to arbitrarily approximate the actual running dynamics. Integrate S p models L corresponding to the sub-running domains p,l,DC to obtain the hybrid semi-parametric model L of the p-th modular domain p,DC , that is, the digital twin model of the p-th modular domain.

[0121] Next, according to the functional or physical connection methods of the p (p = 1, 2,..., m) modular domains, the p (p = 1, 2,..., m) hybrid semi-parametric models L p,DC are derived by multi-scale dynamic integration to obtain the overall digital twin model of the power generation system coupled with the boiler system and the molten salt system. The physical meanings of some or even all of the state variables of this model are known, which is helpful for control design, condition monitoring, etc.

[0122] As Figure 3 shown, this figure is a schematic diagram of a digital twin modeling principle provided by an embodiment of the present application.

[0123] It can be seen from the figure that in this method, first, the structural relationship between the boiler system and the molten salt system and their respective operating mechanisms are determined, then the nodes of the directed graph of the subsystem or equipment are determined, and clustering and domain division are performed. Then, a white-box mechanism parameter model and a black-box parameter model are introduced to obtain a parameter model of domain modularization. Next, a differential dynamic regression vector is defined, then the differential dynamic space is convexly divided, and then the model parameter optimization identification and performance evaluation of domain modularization are performed. The models of different domain modularizations are integrated by multi-scale dynamics, and finally the digital twin model of the boiler system - molten salt system is obtained.

[0124] As Figure 4 shown, this figure is a schematic diagram of the software and hardware structure for implementing the digital twin model provided by an embodiment of the present application.

[0125] Among them, the boiler system - molten salt system coupling unit includes an intelligent operation management system 401, a DCS operation control system 402, and intelligent sensing, data acquisition, and transmission 403. The software architecture of the digital twin system includes a storage module 404, a data thread management 405, a data twin model library 406, a business application and visualization interface 407, a full-excitation simulation system and a DCS control system 408.

[0126] In some embodiments, the software architecture of the digital twin system may also include a real-time data acquisition module, a storage module, a digital twin model creation module, a digital twin model update module, a digital twin model library management module, a digital twin model fusion module, a multi-scenario digital twin operation module, and a business application module for operation control or management.

[0127] Among them, the real-time data acquisition module is mainly used for the real-time operation data acquisition, communication, and governance of the power generation system. The storage module is used for storage and call, facilitating the access and storage of operation data for digital twin modeling. The digital twin model creation module and the digital twin model update module are mainly used for the digital twin modeling, adaptive update, and maintenance of physical subsystems or devices. The digital twin model library management module is mainly used for the classification retrieval, call, and other management of different types of subsystem models. The digital twin model fusion module and the multi-scenario digital twin operation module are mainly used for the digital thread interaction, interconnection, and fusion of multi-subsystem digital twin models for typical scenarios, forming a large system-level integrated digital twin model for typical scenarios. The business application module for operation control or management mainly refers to carrying out business applications such as status monitoring, diagnosis, prediction, and decision optimization based on the established large system-level integrated digital twin model, with the optimization of large system-level operation control or management as the task orientation.

[0128] In some embodiments, data transmission and communication can adopt various communication methods including but not limited to 5G, optical cables, etc., and support various communication protocols including but not limited to TCP / IP, http, WebSocket, MQTT, UDP, IEC, etc. Data governance and storage support time-series databases (including but not limited to databases such as TimescaleDB), relational databases (including but not limited to databases such as PgSQL), distributed file systems (including but not limited to file systems such as Minio), data stream governance (including but not limited to governance methods such as the Spark Streaming framework), and distributed computing (including but not limited to Flink computing engines).

[0129] The digital twin platform adopts a Web architecture. The development languages include, but are not limited to, Golang, Python, JavaScript, C++, etc. The operating systems include, but are not limited to, application engines such as Linux + Docker and Windows + Docker. The model deep learning environment includes, but is not limited to, architectures such as TensorFlow and pytorch. The service monitoring system includes, but is not limited to, Prometheus, and supports dynamic visualization such as 3D, virtual reality, and augmented reality. The data visualization development tools and languages include, but are not limited to, Grafana, JavaScript, react, c#, unity, and lua. The digital twin platform interface supports permission management such as account and password management and business operations with time-limited tokens, supports interactive security management such as WAF and Supervisr monitoring, and supports load balancing management such as LVS and DNS polling.

[0130] It should be noted that the above modules and technology development can be centrally deployed on large servers in the field-type big data center, or a cloud-edge-end collaborative architecture can be adopted for distributed deployment on edge-side or end-side computing devices.

[0131] Based on the above content description, the embodiment of the present application provides a digital twin modeling method for a generator set. The set includes a boiler system, a steam turbine system, and a molten salt system. The method includes: obtaining the structural relationship between the boiler system, the steam turbine system, and the molten salt system; dividing the domain of the set according to the structural relationship to obtain multiple sub-structures; determining the operating principles corresponding to the multiple sub-structures under various working conditions; and performing digital twin modeling on the dominant thermodynamic dynamic characteristics of the set's power generation according to the operating principles corresponding to the multiple sub-structures under various working conditions. It can be seen that in this method, a molten salt system is introduced for data modeling, and the domain of the set is divided and combined with the operating principles under various working conditions, so that the model after digital twin modeling is closer to the actual situation of the set and the accuracy of the model is improved.

[0132] As Figure 5 shown, this figure is a schematic diagram of a digital twin modeling device for a new type of generator set provided by the embodiment of the present application. The set includes a boiler system, a steam turbine system, and a molten salt system. The device includes:

[0133] An acquisition module 501, configured to acquire the structural relationship between the boiler system, the steam turbine system, and the molten salt system;

[0134] A division module 502, configured to divide the domain of the set according to the structural relationship to obtain multiple sub-structures;

[0135] Determination module 503 determines the operating principles corresponding to the multiple sub-structures under various working conditions;

[0136] Modeling module 504 performs digital twin modeling on the power generation characteristics of the unit by using one or more of the algebraic or differential equation mechanism models and data-driven machine learning agent models according to the operating principles corresponding to the multiple sub-structures under various working conditions.

[0137] Optionally, the boiler system includes a boiler, a economizer, a molten salt heat exchanger, a boiler reheater, and a boiler superheater; the steam turbine system includes high-pressure feed water heaters, a deaerator, low-pressure feed water heaters, a low-pressure cylinder, an intermediate-pressure cylinder, a high-pressure cylinder, and the molten salt system includes a molten salt superheater, a molten salt evaporator, a molten salt preheater, a high-temperature molten salt tank, a steam-molten salt heat exchanger, and a low-temperature molten salt tank.

[0138] Optionally, the partitioning module 502 is specifically configured to perform a structural domain partitioning on the unit according to the directed graph node relationship matrix corresponding to the structural relationship, to obtain a plurality of sub-matrices, and the plurality of sub-matrices are used to characterize the multiple sub-structures of the unit.

[0139] Optionally, the partitioning module 502 is specifically configured to process the directed graph node relationship matrix corresponding to the structural relationship by using a directed graph node clustering algorithm, so as to perform a structural domain partitioning on the unit.

[0140] Optionally, the acquisition module 501 is further configured to acquire the actual operating data corresponding to the unit during the power generation process under the various working conditions;

[0141] The modeling module 504 is specifically configured to perform digital twin modeling on the power generation characteristics of the unit according to the operating principles corresponding to the multiple sub-structures under various working conditions.

[0142] Through the description of the above embodiments, those skilled in the art can clearly understand that for the convenience and conciseness of description, only the above division of each functional module is used as an example. In actual applications, the above functions can be allocated to different functional modules according to needs, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. The specific working processes of the systems, devices, and units described above can refer to the corresponding processes in the foregoing method embodiments, and will not be elaborated herein.

[0143] In several embodiments provided in this embodiment, it should be understood that the disclosed processing device and method can be implemented in other ways. The device embodiments described above are merely illustrative. For example, the division of the modules or units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed coupling or direct coupling or communication connection to each other can be through some interfaces. The indirect coupling or communication connection of the device or unit can be in an electrical, mechanical or other form.

[0144] The units described as separate components may or may not be physically separated. The components displayed as units may or may not be physical units, that is, they can be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0145] In addition, in each embodiment of this embodiment, the functional units can be integrated in a processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit. The above integrated units can be implemented in the form of hardware or in the form of software functional units.

[0146] If the above integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this embodiment, in essence, or the part that contributes to the prior art, or all or part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) or a processor to execute all or part of the steps of the method described in each embodiment. The aforementioned storage medium includes: flash memory, mobile hard disk, read-only memory, random access memory, magnetic disk, or optical disk and other various media that can store program codes.

[0147] The embodiment of the present application also provides a computer-readable storage medium, which is used to store a computer program, and the computer program is used to execute the method described in any one of the above method embodiments.

[0148] The embodiment of the present application also provides a computer program product, on which a computer program is stored. When the program is executed by a processing device, it implements the method described in any one of the above method embodiments.

[0149] As described above, it is only the specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any changes or substitutions within the technical scope disclosed in the present application should be covered within the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claimed rights.

Claims

1. A digital twin modeling method for a generator set, characterized in that The unit includes a boiler system, a steam turbine system, and a molten salt system. The method includes: Obtaining the structural relationship between the boiler system, the steam turbine system, and the molten salt system; Using the directed graph node clustering algorithm to process the directed graph node relationship matrix corresponding to the structural relationship, and performing domain partitioning on the unit according to the operating principle of the unit, prior knowledge, and the domain partitioning knowledge base constructed based on the coupled flexible power generation system, to obtain multiple sub-matrices, where the multiple sub-matrices are used to represent multiple sub-structures of the unit. Each element in the directed graph node relationship matrix represents the connection relationship between the corresponding nodes; Determining the operating principles corresponding to the multiple sub-structures under multiple operating conditions, where the operating principles are characterized by the modular integrated parameter models corresponding to each domain. The modular integrated parameter models are obtained by multi-scale dynamic integration and derivation of the models of different subsystems or devices using a multi-stage series, multi-stage parallel, or multi-stage hybrid series / parallel connection method based on the functional and physical connection relationships, white box mechanism models, or black box parameter models between different subsystems or devices; Performing digital twin modeling on the power generation characteristics of the unit according to the operating principles corresponding to the multiple sub-structures under multiple operating conditions.

2. The method according to claim 1, characterized in that, The boiler system includes a boiler, an economizer, a molten salt heat exchanger, a boiler reheater, a boiler superheater, a first valve, a first hydraulic / electric pump, and a first pipeline; the steam turbine system includes high-pressure feed water heaters, a deaerator, low-pressure feed water heaters, a low-pressure cylinder, a medium-pressure cylinder, a high-pressure cylinder, a second valve, a second hydraulic / electric pump, and a second pipeline; the molten salt system includes a molten salt superheater, a molten salt evaporator, a molten salt preheater, a high-temperature molten salt tank, a steam-molten salt heat exchanger, a low-temperature molten salt tank, a third valve, a third hydraulic / electric pump, and a third pipeline.

3. The method according to claim 1, characterized in that The method further includes: Obtaining the actual operating data corresponding to the multiple operating conditions during the power generation process of the unit; The performing digital twin modeling on the power generation characteristics of the unit according to the operating principles corresponding to the multiple sub-structures under multiple operating conditions includes: Performing digital twin modeling on the power generation characteristics of the unit according to the operating principles corresponding to the multiple sub-structures under multiple operating conditions and the actual operating data.

4. A digital twin modeling device for a generator set, characterized in that, The unit includes a boiler system, a steam turbine system, and a molten salt system. The device includes: An obtaining module, configured to obtain the structural relationship between the boiler system, the steam turbine system, and the molten salt system; A partitioning module, which uses the directed graph node clustering algorithm to process the directed graph node relationship matrix corresponding to the structural relationship, and performs domain partitioning on the unit according to the operating principle of the unit, prior knowledge, and the domain partitioning knowledge base constructed based on the coupled flexible power generation system, to obtain multiple sub-matrices, where the multiple sub-matrices are used to represent multiple sub-structures of the unit. Each element in the directed graph node relationship matrix represents the connection relationship between the corresponding nodes; A determination module determines the operating principles corresponding to the multiple sub-structures under various working conditions, wherein the operating principles are characterized by modular integrated parameter models corresponding to each structural domain, and the modular integrated parameter models are obtained by multi-scale dynamic integration and derivation of models of different subsystems or devices based on the functional and physical connection relationships, white-box mechanism models or black-box parameter models between different subsystems or devices, and adopting a multi-stage series, multi-stage parallel or multi-stage hybrid series / parallel connection method; A modeling module performs digital twin modeling of the power generation characteristics of the unit by using one or more of an algebraic or differential equation mechanism model and a data-driven machine learning agent model according to the operating principles corresponding to the multiple sub-structures under various working conditions.

5. The device according to claim 4, characterized in that, The boiler system includes a boiler, an economizer, a molten salt heat exchanger, a boiler reheater, a boiler superheater, a first valve, a first hydraulic / electric pump, and a first pipeline; the steam turbine system includes high-pressure feed water heaters, a deaerator, low-pressure feed water heaters, a low-pressure cylinder, an intermediate-pressure cylinder, a high-pressure cylinder, a second valve, a second hydraulic / electric pump, and a second pipeline; the steam turbine system includes a molten salt superheater, a molten salt evaporator, a molten salt preheater, a high-temperature molten salt tank, a steam-molten salt heat exchanger, a low-temperature molten salt tank, a third valve, a third hydraulic / electric pump, and a third pipeline.

6. A computer-readable storage medium, characterized in that, The computer-readable storage medium is used to store a computer program, and the computer program is used to execute the method according to any one of claims 1-3.

7. A computer program product having a computer program stored thereon, characterized in that, When the program is executed by a processing device, the method according to any one of claims 1 to 3 is implemented.

Images