Heat supply system dynamic coupling modeling method and system based on digital twinning

Abstract

The invention relates to the technical field of heat supply systems, and discloses a dynamic coupling modeling method and system for a heat supply system based on digital twinning, and the method comprises the steps: obtaining the operation data of the heat supply system, and constructing and operating a plurality of sub-models according to the operation data; obtaining state data of each sub-model, and generating a state correction factor of each sub-model; setting a standard time step length for each sub-model, and correcting according to the state correction factor to obtain a corrected time step length; setting a standard synchronization point of each sub-model; obtaining state data of the sub-model, and setting a correction synchronization point according to the state data and the standard synchronization point; acquiring transmission data packets among the sub-models, and dividing intensity grades for data in the data packets; and setting a transmission strategy based on the corrected synchronization point and the strength level. According to the method, the overall operation efficiency is improved by coordinating data exchange among all the models, the alternating current frequency among the models can be accurately judged through an event recognition method, and the operand can be reduced.

Description

Technical Field

[0001] This application relates to the field of heating system technology, and in particular to a dynamic coupling modeling method and system for heating systems based on digital twins. Background Technology

[0002] Digital twin modeling of heating systems is a key technology that enables real-time monitoring, simulation prediction, and optimized control of the operating status of heating systems by constructing a virtual mapping of the physical system.

[0003] Existing modeling methods suffer from the following technical shortcomings: First, the model building process relies on human experience and lacks a systematic multi-model coupling mechanism. In traditional methods, the boundary delineation and interface design of hydraulic, thermal, and load models are mainly based on the subjective experience of engineers, lacking objective and quantitative criteria. This results in insufficient coupling accuracy between models, making it difficult to accurately reflect the true dynamic characteristics of complex heating systems.

[0004] Secondly, the ability to perform multi-timescale co-simulation is insufficient. In heating systems, hydraulic processes, thermal processes, and load responses correspond to different timescales of milliseconds, minutes, and hours, respectively. Existing methods struggle to achieve organic coordination of these different scale models. A crudely unified time step leads to either wasted computational resources or loss of key dynamic features, particularly failing to effectively capture transient processes such as water hammer. Summary of the Invention

[0005] To address the aforementioned technical issues, this application provides a dynamic coupling modeling method and system for heating systems based on digital twins. The aim is to obtain a technical solution that can link models with different time steps, improve overall operating efficiency, accurately determine the frequency of data exchange between models through event recognition, make the operating results closer to the real situation, and reduce the amount of computation.

[0006] In some embodiments of this application, a dynamic coupling modeling method for a heating system based on digital twins is provided, characterized by comprising:

[0007] Acquire the operating data of the heating system, and construct and run multiple sub-models based on the operating data;

[0008] Obtain the state data of each sub-model and generate the state correction factor for each sub-model;

[0009] Set a standard time step for each sub-model, and obtain the corrected time step based on the state correction factor;

[0010] Set the standard synchronization points for each sub-model;

[0011] Obtain the state data of the sub-model, and set a correction synchronization point based on the state data and the standard synchronization point;

[0012] Obtain the transmission data packets between each sub-model, and classify the data in the data packets into intensity levels;

[0013] The transmission strategy is set based on the modified synchronization point and intensity level.

[0014] In some embodiments of this application, generating the state correction factors for each sub-model includes:

[0015] Real-time acquisition of one type of state parameters for each sub-model;

[0016] Set a threshold for the rate of change of each type of state parameter, and calculate the rate of change of the type of state parameter;

[0017] A state index value is generated based on the rate of change and the rate of change threshold;

[0018] A state correction factor is generated based on the state index value.

[0019] In some embodiments of this application, the generation of state indicator values ​​includes:

[0020] Construct a sequence of state parameters of a single sub-model, C, Z = (C1, C2, ..., Cm, ..., Cn), where C1 is the first state parameter of the sub-model; C2 is the second state parameter of the sub-model; Cm is the mth state parameter of the sub-model; and n is the total number of state parameters of the sub-model.

[0021] Obtain the rate of change and the rate of change threshold of each first state parameter in Z;

[0022] Calculate the state index value Z of a single sub-model 指 ;

[0023]

[0024] Among them, Z 指 Here are the state index values ​​for a single sub-model; km is the weighting coefficient of Cm; Bm is the rate of change of Cm; B 阈 m is the rate of change threshold of Cm; n is the total number of state parameters of a class of sub-models.

[0025] In some embodiments of this application, generating a state correction factor based on a state index value includes:

[0026] Set the threshold values ​​for the first state index value X1, the threshold values ​​for the second state index value X2, the threshold values ​​for the first correction factor Z1, and the threshold values ​​for the second correction factor Z2.

[0027] Calculate the state correction factor Z for each sub-model.修 ;

[0028] For Z 指 Sub-models whose values ​​exceed the threshold of the first state index, Z 修 =Z1;

[0029] For Z 指 Sub-models whose values ​​are less than the threshold of the second state index, Z 修 =Z2;

[0030] For a sub-model where Z is greater than the second state index threshold and less than the first state index threshold, Z... 修 =1-(X2-Z) 指 ) / (Z 指 -X1).

[0031] In some embodiments of this application, the step of obtaining the correction time step based on the state correction factor includes:

[0032] Obtain the standard time step and state correction factor for each sub-model;

[0033] Calculate the corrected time step T for each sub-model 修 ;

[0034] T 修 =Z 修 *T 标 ;

[0035] Among them, T 修 To adjust the time step; T 标 This is the standard time step.

[0036] In some embodiments of this application, the setting of the correction synchronization point includes:

[0037] Extract the standard synchronization points of each sub-model;

[0038] Define the event condition set for each sub-model and generate event synchronization points;

[0039] A fusion synchronization point is generated based on the standard synchronization point and the event synchronization point;

[0040] The fusion synchronization point is corrected based on the corrected time step of each sub-model.

[0041] In some embodiments of this application, the step of setting the event condition set for each sub-model and generating event synchronization points includes:

[0042] Establish an event condition set for each sub-model;

[0043] The event condition set is divided according to event type to obtain multiple sub-event sets;

[0044] Set trigger conditions for each sub-event set;

[0045] When the acquired runtime data meets the triggering conditions, it is set as an event synchronization point.

[0046] In some embodiments of this application, generating a fused synchronization point based on the standard synchronization point and the event synchronization point includes:

[0047] Obtain the standard synchronization points of each sub-model, and set every two standard synchronization points as a standard cycle;

[0048] Set the synchronization point interval threshold;

[0049] The standard period for satisfying synchronization points with an interval less than the synchronization point interval threshold is set as the problem period;

[0050] Obtain time synchronization point data for each problem cycle;

[0051] Set the priority weights of event synchronization points corresponding to various sub-event sets;

[0052] When multiple event synchronization points have the same weight, the earliest time synchronization point in the problem period is retained; when multiple event synchronization points are less than the synchronization point interval threshold, the time synchronization point with the highest priority weight is retained.

[0053] In some embodiments of this application, obtaining the corrected synchronization point includes:

[0054] Obtain the standard time step and the corrected time step corresponding to each fusion synchronization point;

[0055] Obtain time data from each fusion synchronization point;

[0056] Generate the time data of the corrected synchronization point based on the standard time step and the corrected time step;

[0057] T 修 =T 融 / (1+Bm / B 阈 m*β);

[0058] Among them, T 修 To correct the time data of the time step, T 融 β is the step size correction factor for merging time data at different time steps.

[0059] This application also provides a dynamic coupling modeling system for a heating system based on digital twins, including:

[0060] The model unit is used to acquire the operating data of the heating system and construct and run multiple sub-models based on the operating data.

[0061] The central control unit is used to set the correction time step and correction synchronization point according to the sub-model;

[0062] The central control unit includes:

[0063] The first control module is used to acquire the state data of each sub-model and generate the state correction factor of each sub-model.

[0064] The second control module is used to set a standard time step for each sub-model and to obtain a corrected time step based on the state correction factor.

[0065] The third control module is used to set the standard synchronization points for each sub-model.

[0066] The fourth control module is used to acquire the state data of the sub-model and set a correction synchronization point based on the state data and the standard synchronization point.

[0067] The fifth control module is used to acquire data packets between various sub-models and to classify the data in the data packets into intensity levels;

[0068] An execution unit is used to set a transmission strategy based on the corrected synchronization point and intensity level. Compared with existing technologies, the dynamic coupling modeling method and system for a heating system based on digital twins in this application embodiment have the following advantages:

[0069] A complete dynamic coupling simulation architecture for heating systems across multiple time scales was constructed, enabling precise data interaction and collaborative simulation between models with different time steps. This method innovatively proposes an adaptive step size adjustment method based on state correction factors and an intelligent synchronization strategy based on event triggering by establishing a multi-model coupling mechanism for hydraulic, thermal, and load models. This effectively solves the technical challenge of balancing computational efficiency and simulation accuracy in traditional modeling methods.

[0070] Meanwhile, this method enables the quantitative evaluation of the system's dynamic characteristics by real-time monitoring of the change rate of the core state parameters of each sub-model, and automatic adjustment of the simulation step size. This improves computational efficiency when the system is stable and ensures simulation accuracy when it is dynamically changing. Finally, a data transmission mechanism based on intensity levels is established. By quantitatively scoring and classifying the data transmitted between models, a differentiated transmission strategy is implemented to ensure the timeliness and integrity of key data. Attached Figure Description

[0071] Figure 1 This is a flowchart illustrating a dynamic coupling modeling method for a heating system based on digital twins, as described in an embodiment of this application. Detailed Implementation

[0072] The specific embodiments of this application will be described in further detail below with reference to the accompanying drawings and examples. The following examples are used to illustrate this application, but are not intended to limit the scope of this application.

[0073] In the description of this application, it should be understood that the terms "center", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are only for the convenience of describing this application and 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 this application.

[0074] The terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this application, unless otherwise stated, "a plurality of" means two or more.

[0075] In the description of this application, it should be noted that, unless otherwise expressly specified and limited, the terms "installation," "connection," and "linking" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection between two components. Those skilled in the art can understand the specific meaning of the above terms in this application based on the specific circumstances.

[0076] like Figure 1 As shown in the figure, an embodiment of this application provides a dynamic coupling modeling method for a heating system based on digital twins, comprising:

[0077] Acquire operational data of the heating system, and construct and run multiple sub-models based on the operational data;

[0078] Obtain the state data of each sub-model and generate the state correction factor for each sub-model;

[0079] Set a standard time step for each sub-model, and then adjust the time step according to the state correction factor to obtain the corrected time step;

[0080] Set the standard synchronization points for each sub-model;

[0081] Obtain the state data of the sub-model, and set the correction synchronization point based on the state data and the standard synchronization point;

[0082] Obtain the data packets transmitted between the various sub-models and classify the data in the data packets into strength levels;

[0083] The transmission strategy is set based on the modified synchronization point and strength level.

[0084] Specifically, the time step is the data processing cycle between different models, which is the interval between multiple data exchanges between different models.

[0085] Specifically, operational data refers to the data generated by the heating system during operation, including hydraulic data, thermal data, and load data.

[0086] Specifically, the sub-models include: hydraulic model, thermal model, and load model.

[0087] Specifically, the state data of the hydraulic model includes: pipeline pressure, fluid flow rate, pump speed, and valve opening; the state data of the thermal model includes: supply water temperature, return water temperature, and heat meter readings; and the state data of the load model includes: building indoor temperature, outdoor temperature, and future weather forecast.

[0088] Specifically, the standard time step is the period during which each sub-model processes data; the hydraulic model is preferably 10ms; the thermal model is preferably 1s; and the load model is preferably 1min.

[0089] Specifically, the state correction factor is used to adjust the data processing cycle based on the operating state of the heating system. For example, when the hydraulic data changes drastically, i.e., when u needs to be processed more frequently.

[0090] Specifically, the hydraulic model is simplified by performing intrinsic orthogonal decomposition (POD) on the complex 3D pipe network CFD model. Flow field snapshots under 1000 different operating conditions are collected, and the top 20 dominant modes are extracted through eigenvalue decomposition. The original model with millions of grid points is simplified to a 20-dimensional system of ordinary differential equations, increasing computational speed by approximately 200 times while preserving crucial pressure wave dynamics. The load model is also simplified by constructing a surrogate model based on Gaussian process regression (GPR). One year of historical operating data (outdoor temperature, date type, time point, and actual load) is used for training, replacing the original complex LSTM network. This surrogate model reduces inference time from 50ms to 5ms while maintaining prediction accuracy.

[0091] Specifically, the correction time step is a more realistic data processing cycle obtained after correction by the correction factor generated by the real-time running status.

[0092] Specifically, the strength levels are divided, and a transmission strategy is set based on the corrected synchronization point and the strength level. This includes: obtaining the data type in the data packet; calculating the comprehensive score P for each data item; P = k1*G + k2*E; where k1 is the first coefficient for each data item; k2 is the second coefficient for each data item; G is the update frequency for each data item; and E is the security coefficient. When P is greater than the first score threshold, it is classified as Level 1 strength data; when P is greater than the second score threshold but less than the first score threshold, it is classified as Level 2 strength data. For Level 1 strength data, the first strategy is adopted; for Level 2 strength data, the second strategy is adopted. Specifically, the first strategy uses an instantaneous unconditional transmission mechanism for Level 1 strength data, which is not limited by the synchronization point time; it sends data as soon as it is detected, with a transmission delay requirement of less than 100 milliseconds. The Level 2 transmission strategy uses a corrected synchronization point priority transmission mechanism for Level 2 strength data, prioritizing transmission within a determined corrected synchronization point time, with a transmission delay requirement of less than 1 second. Level 1 strength data is defined as data where P is greater than the first score threshold. The first score threshold is preferably 0.7. This type of data includes equipment fault alarms, safety protection commands, and water hammer warning signals. Secondary intensity data is defined as P being greater than the second scoring threshold and less than or equal to the first scoring threshold. The second scoring threshold is preferably 0.4. This type of data includes core state variables (such as pressure, flow rate, and temperature), optimized control commands, load forecast data, etc., which affect system operating efficiency but are not urgent. Update frequency indicates how frequently the data is updated. The safety coefficient indicates the degree of impact of the data on the safe operation of the system, with a value ranging from 0 to 1. The first and second coefficients represent the importance of update frequency and safety in the comprehensive score, respectively, and k1 + k2 = 1; k1 is preferably 0.3, and k2 is preferably 0.7.

[0093] In some embodiments of this application, the state correction factors for each sub-model are generated, including:

[0094] Real-time acquisition of one type of state parameters for each sub-model;

[0095] Set the threshold for the rate of change of each type of state parameter, and calculate the rate of change of each type of state parameter;

[0096] State index values ​​are generated based on the rate of change and the rate of change threshold;

[0097] A state correction factor is generated based on the state index value.

[0098] Specifically, the change rate thresholds are as follows: pressure change rate threshold is preferably 500 Pa / s; flow rate change rate threshold is preferably 0.2 m3 / s2; temperature change rate threshold is preferably 0.5 ℃ / s; predicted load change rate threshold is preferably 8% / min; and prediction deviation rate threshold is preferably 12%.

[0099] Specifically, the state parameters include: for hydraulic models, the pressure change rate and flow rate change rate; for thermal models, the temperature change rate and heat accumulation deviation rate; and for load models, the predicted load change rate and prediction deviation rate.

[0100] Specifically, the rate of change refers to the amount of change in the state parameters per unit time, calculated by the following formula: B = |S(t) - S(t-Δt)| / Δt; where B is the rate of change, S(t) is the state parameter value at the current moment, S(t-Δt) is the state parameter value at the previous time step, and Δt is the time step size.

[0101] In some embodiments of this application, generating status indicator values ​​includes:

[0102] Construct a sequence of state parameters of a single sub-model, C, Z = (C1, C2, ..., Cm, ..., Cn), where C1 is the first state parameter of the sub-model; C2 is the second state parameter of the sub-model; Cm is the mth state parameter of the sub-model; and n is the total number of state parameters of the sub-model.

[0103] Obtain the rate of change and the rate of change threshold of each first state parameter in Z;

[0104] Calculate the state index value Z of a single sub-model 指 ;

[0105]

[0106] Among them, Z 指 Here are the state index values ​​for a single sub-model; km is the weighting coefficient of Cm; Bm is the rate of change of Cm; B 阈 m is the rate of change threshold of Cm; n is the total number of state parameters of a class of sub-models.

[0107] Specifically, the weighting coefficients represent the degree of influence of each sub-model on the final heating supply during the operation of the entire heating system, including: hydraulic model weighting coefficients: where the pressure change rate weight is preferably 0.6; the flow rate change rate weight is preferably 0.4; thermal model weighting coefficients: the temperature change rate weight is preferably 0.7; the cumulative heat deviation weight is preferably 0.3; load model weighting coefficients: the predicted load change rate weight is preferably 0.5; the prediction deviation rate weight is preferably 0.5.

[0108] In some embodiments of this application, a state correction factor is generated based on a state index value, including:

[0109] Set the threshold values ​​for the first state index value X1, the threshold values ​​for the second state index value X2, the threshold values ​​for the first correction factor Z1, and the threshold values ​​for the second correction factor Z2.

[0110] Calculate the state correction factor Z for each sub-model. 修 ;

[0111] For Z 指 Sub-models whose values ​​exceed the threshold of the first state index, Z 修 =Z1

[0112] For Z 指 Sub-models whose values ​​are less than the threshold of the second state index, Z 修 =Z2

[0113] For Z 指 Sub-models whose Z values ​​are greater than the second state index threshold and less than the first state index threshold. 修 =1-(X2-Z) 指 ) / (Z 指 -X1).

[0114] Specifically, the first state index threshold and the second state index threshold are critical values ​​describing the operating state of the heating system. The first state is the upper limit of a relatively drastic operating state; exceeding this value will lead to system failure. The second state is the minimum operating state for normal operation. The first state index threshold X1 is preferably 1.2; the second state index threshold X2 is preferably 0.8.

[0115] Specifically, the correction factor threshold describes the degree of influence of the state index on the sub-model. The first correction factor threshold Z1 is preferably 0.2, and the second correction factor threshold Z2 is preferably 1.5.

[0116] In some embodiments of this application, the corrected time step is obtained based on the state correction factor, including:

[0117] Obtain the standard time step and state correction factor for each sub-model;

[0118] Calculate the corrected time step T for each sub-model 修 ;

[0119] T 修 =Z 修 *T 标 ;

[0120] Among them, T 修 To adjust the time step; T 标 This is the standard time step.

[0121] In some embodiments of this application, setting a corrected synchronization point includes:

[0122] Extract the standard synchronization points of each sub-model;

[0123] Define the event condition set for each sub-model and generate event synchronization points;

[0124] Generate a fusion synchronization point based on the standard synchronization point and the event synchronization point;

[0125] The fusion synchronization point is obtained by correcting the time step of each sub-model.

[0126] Specifically, the preferred data exchange period between the various models at the standard synchronization point is 300 seconds.

[0127] Specifically, the event condition set includes: hydraulic model event condition set: pressure change event; flow anomaly event; equipment failure event; thermal model event condition set: temperature drop event; heat imbalance event; load model event condition set: prediction large correction event; meteorological warning event.

[0128] In some embodiments of this application, event condition sets are set for each sub-model, and event synchronization points are generated, including:

[0129] Establish an event condition set for each sub-model;

[0130] The event condition set is divided according to event type to obtain multiple sub-event sets;

[0131] Set trigger conditions for each sub-event set;

[0132] When the acquired runtime data meets the triggering conditions, it is set as an event synchronization point.

[0133] Specifically, the event types are: emergency security events (abnormal situations that directly affect system security); performance anomaly events (deviations that affect system performance); and prediction update events (significant changes in the output of the prediction model).

[0134] Specifically, the triggering conditions include: hydraulic model triggering conditions: pressure change: dP / dt>750Pa / s; abnormal flow: |Qactual - QSet|>25m3 / h for 30 seconds; equipment failure: abnormal pump / valve status signal; thermal model triggering conditions: temperature drop: dT / dt>0.8°C / s; heat imbalance: |heat supply - load|>300kW for 2 minutes; load model triggering conditions: significant prediction correction: predicted load change>15%; weather warning: receiving cold wave / strong wind warning signal.

[0135] In some embodiments of this application, a fused synchronization point is generated based on a standard synchronization point and an event synchronization point, including:

[0136] Obtain the standard synchronization points of each sub-model, and set every two standard synchronization points as a standard cycle;

[0137] Set the synchronization point interval threshold;

[0138] The standard period for satisfying synchronization points with an interval less than the synchronization point interval threshold is set as the problem period;

[0139] Obtain time synchronization point data for each problem cycle;

[0140] Set the priority weights of event synchronization points corresponding to various sub-event sets;

[0141] When multiple event synchronization points have the same weight, the earliest time synchronization point in the problem cycle is retained; when multiple event synchronization points are less than the synchronization point interval threshold, the time synchronization point with the highest priority weight is retained.

[0142] Specifically, the synchronization point interval threshold, which is the minimum interval for data exchange between different models, is preferably 180 seconds.

[0143] Specifically, the standard synchronization point is the preset period for data exchange between the various sub-models. For example, pressure and flow data from the hydraulic model need to be transmitted to the thermal model. Information such as temperature distribution and heat loss output by the thermal model is fed back to the hydraulic model, preferably every 5 minutes.

[0144] Specifically, the synchronization point is adjusted to be the data exchange cycle between models after taking into account the actual operating status of the heating system.

[0145] In some embodiments of this application, the corrected synchronization point is obtained, including:

[0146] Obtain the standard time step and the corrected time step corresponding to each fusion synchronization point;

[0147] Obtain time data from each fusion synchronization point;

[0148] Generate time data for the corrected synchronization point based on the standard time step and the corrected time step;

[0149] T 修 =T 融 / (1+Bm / B 阈 m*β);

[0150] Among them, T 修 To correct the time data of the time step, T 融 β is the step size correction factor for merging time data at different time steps.

[0151] Specifically, the preferred value for controlling the influence of the rate of change on the synchronization interval is 2.0.

[0152] This application also provides a dynamic coupling modeling system for a heating system based on digital twins, including:

[0153] Model units are used to acquire operational data of the heating system and to build and run multiple sub-models based on the operational data.

[0154] The central control unit is used to set the correction time step and correction synchronization point according to the sub-model;

[0155] The central control unit includes:

[0156] The first control module is used to acquire the state data of each sub-model and generate the state correction factor of each sub-model.

[0157] The second control module is used to set the standard time step for each sub-model and to obtain the corrected time step based on the state correction factor.

[0158] The third control module is used to set the standard synchronization points for each sub-model.

[0159] The fourth control module is used to acquire the state data of the sub-model and set the correction synchronization point based on the state data and the standard synchronization point.

[0160] The fifth control module is used to acquire data packets between various sub-models and classify the data in the data packets into intensity levels;

[0161] The execution unit is used to set the transmission strategy based on the modified synchronization point and strength level.

[0162] The above are merely preferred embodiments of this application. It should be noted that, for those skilled in the art, several improvements and substitutions can be made without departing from the technical principles of this application, and these improvements and substitutions should also be considered within the scope of protection of this application.

Claims

1. A dynamic coupling modeling method for a heating system based on digital twins, characterized in that, include: Acquire the operating data of the heating system, and construct and run multiple sub-models based on the operating data; Obtain the state data of each sub-model and generate the state correction factor for each sub-model; Set a standard time step for each sub-model, and obtain the corrected time step based on the state correction factor; Set the standard synchronization points for each sub-model; Obtain the state data of the sub-model, and set a correction synchronization point based on the state data and the standard synchronization point; Acquire data packets between each sub-model and classify the data in the data packets into intensity levels; The transmission strategy is set based on the modified synchronization point and intensity level.

2. The dynamic coupling modeling method for a heating system based on digital twins as described in claim 1, characterized in that, The state correction factors for generating each sub-model include: Real-time acquisition of one type of state parameters for each sub-model; Set a threshold for the rate of change of each type of state parameter, and calculate the rate of change of the type of state parameter; A state index value is generated based on the rate of change and the rate of change threshold; A state correction factor is generated based on the state index value.

3. The dynamic coupling modeling method for a heating system based on digital twins as described in claim 2, characterized in that, The generated status index values ​​include: Construct a sequence of state parameters of a single sub-model, C, Z = (C1, C2, ..., Cm, ..., Cn), where C1 is the first state parameter of the sub-model; C2 is the second state parameter of the sub-model; Cm is the mth state parameter of the sub-model; and n is the total number of state parameters of the sub-model. Obtain the rate of change and the rate of change threshold of each first state parameter in Z; Calculate the state index value Z of a single sub-model 指 ; Among them, Z 指 Here are the state index values ​​for a single sub-model; km is the weighting coefficient of Cm; Bm is the rate of change of Cm; B 阈 m is the rate of change threshold of Cm; n is the total number of state parameters of a class of sub-models.

4. The dynamic coupling modeling method for a heating system based on digital twins as described in claim 3, characterized in that, The step of generating a state correction factor based on the state index value includes: Set the threshold values ​​for the first state index value X1, the threshold values ​​for the second state index value X2, the threshold values ​​for the first correction factor Z1, and the threshold values ​​for the second correction factor Z2. Calculate the state correction factor Z for each sub-model. 修 ; For Z 指 Sub-models whose values ​​exceed the threshold of the first state index, Z 修 =Z1; For Z 指 Sub-models whose values ​​are less than the threshold of the second state index, Z 修 =Z2; For a sub-model where Z is greater than the second state index threshold and less than the first state index threshold, Z... 修 =1-(X2-Z) 指 ) / (Z 指 -X1).

5. The dynamic coupling modeling method for a heating system based on digital twins as described in claim 4, characterized in that, The step of obtaining the corrected time step based on the state correction factor includes: Obtain the standard time step and state correction factor for each sub-model; Calculate the corrected time step T for each sub-model 修 ; T 修 =Z 修 *T 标 ; Among them, T 修 To adjust the time step; T 标 This is the standard time step.

6. The dynamic coupling modeling method for a heating system based on digital twins as described in claim 1, characterized in that, The setting of the correction synchronization point includes: Extract the standard synchronization points of each sub-model; Define the event condition set for each sub-model and generate event synchronization points; A fusion synchronization point is generated based on the standard synchronization point and the event synchronization point; The fusion synchronization point is corrected based on the corrected time step of each sub-model.

7. The dynamic coupling modeling method for a heating system based on digital twins as described in claim 6, characterized in that, The process of setting event condition sets for each sub-model and generating event synchronization points includes: Establish an event condition set for each sub-model; The event condition set is divided according to event type to obtain multiple sub-event sets; Set trigger conditions for each sub-event set; When the acquired runtime data meets the triggering conditions, it is set as an event synchronization point.

8. The dynamic coupling modeling method for a heating system based on digital twins as described in claim 7, characterized in that, The process of generating a fused synchronization point based on the standard synchronization point and the event synchronization point includes: Obtain the standard synchronization points of each sub-model, and set every two standard synchronization points as a standard cycle; Set the synchronization point interval threshold; The standard period for satisfying synchronization points with an interval less than the synchronization point interval threshold is set as the problem period; Obtain time synchronization point data for each problem cycle; Set the priority weights of event synchronization points corresponding to various sub-event sets; When multiple event synchronization points have the same weight, the earliest time synchronization point in the problem period is retained; when multiple event synchronization points are less than the synchronization point interval threshold, the time synchronization point with the highest priority weight is retained.

9. The dynamic coupling modeling method for a heating system based on digital twins as described in claim 8, characterized in that, The process of obtaining the corrected synchronization point includes: Obtain the standard time step and the corrected time step corresponding to each fusion synchronization point; Obtain time data from each fusion synchronization point; Generate the time data of the corrected synchronization point based on the standard time step and the corrected time step; T 修 =T 融 / (1+Bm / B 阈 m*β); Among them, T 修 To correct the time data of the time step, T 融 β is the step size correction factor for merging time data at different time steps.

10. A dynamic coupling modeling system for a heating system based on digital twins, used to execute the dynamic coupling modeling method for a heating system based on digital twins as described in any one of claims 1-9, characterized in that, include: The model unit is used to acquire the operating data of the heating system and construct and run multiple sub-models based on the operating data. The central control unit is used to set the correction time step and correction synchronization point according to the sub-model; The central control unit includes: The first control module is used to acquire the state data of each sub-model and generate the state correction factor of each sub-model. The second control module is used to set a standard time step for each sub-model and to obtain a corrected time step based on the state correction factor. The third control module is used to set the standard synchronization points for each sub-model. The fourth control module is used to acquire the state data of the sub-model and set a correction synchronization point based on the state data and the standard synchronization point. The fifth control module is used to acquire data packets between various sub-models and to classify the data in the data packets into intensity levels; An execution unit is used to set a transmission strategy based on the modified synchronization point and intensity level.

Images