A thermal power plant operation optimization method and system based on digital twin technology

Abstract

This invention relates to the field of thermal power plant technology, and provides a method and system for optimizing the operation of thermal power plants based on digital twin technology, including the following steps: Step S1, acquiring the physical mechanism and historical operating data of the thermal power plant's generator units, processing and storing the data; Step S2, establishing a digital twin model of the thermal power plant's generator units based on the physical mechanism and historical operating data. This invention, by establishing a digital twin model linked to the optimization algorithm, realizes the dynamic transformation of economic dispatch in thermal power plants, ensuring that load allocation schemes are not only based on the actual capacity of the units, but also predict safety risks during execution, preventing the optimization results from deviating from the actual optimal solution due to model lag, and improving the economy and safety of power plant operation. By introducing marginal cost range constraints based on equipment health status and a closed-loop optimization mechanism, adaptive economic dispatch under safety constraints is achieved.

Description

Technical Field

[0001] This invention relates to the field of thermal power generation technology, and in particular to a method and system for optimizing the operation of thermal power plants based on digital twin technology. Background Technology

[0002] A thermal power plant, or coal-fired power plant for short, is a factory that uses combustible materials (such as coal) as fuel to produce electricity. With the advancement of my country's carbon neutrality strategy and the deepening of power market reforms, thermal power plants face pressure to conserve energy, reduce emissions, and improve efficiency. Against this backdrop, utilizing digital twin technology to construct intelligent systems that map the physical and virtual worlds has become an important way for the thermal power industry to achieve digital transformation. Digital twin technology, by integrating physical mechanisms, real-time data, and advanced algorithms, can reproduce physical units in virtual space, providing a new technical path for assessing operational status and making optimization decisions.

[0003] Currently, most digital twin systems focus on equipment status monitoring and fault diagnosis. For example, existing invention patent CN118536638B discloses a power optimization method and system based on intelligent data processing and analysis and digital twins. This patent analyzes data using the EMD algorithm, which can accurately identify and effectively classify problems in the power system. This improves the efficiency of problem diagnosis and provides a reliable basis for selecting and matching the most suitable solution. By constructing a digital twin model of the power system, this invention enables the solution to be fully tested and verified before practical application.

[0004] However, this solution and similar existing technologies have the following problems when optimizing the operation of thermal power plants:

[0005] 1. Existing digital twin models are mainly used for condition monitoring and post-event simulation. They are not combined with real-time load allocation algorithms and cannot be directly called to calculate core economic parameters and physical boundaries. This results in the data model on which decisions are based being outdated and unable to reflect the true capacity of the units.

[0006] 2. Traditional constant incremental rate optimization relies on fixed design coal consumption curves or historical average data. When the unit's performance declines due to aging or other reasons, the optimization results based on static data deviate significantly from the actual optimal solution, resulting in poor optimization capability.

[0007] To address this, a method and system for optimizing the operation of thermal power plants based on digital twin technology is proposed. Summary of the Invention

[0008] In view of this, the present invention provides a method and system for optimizing the operation of thermal power plants based on digital twin technology, in order to solve or alleviate one of the technical problems existing in the prior art, and at least provide a beneficial option.

[0009] The technical solution of this invention is implemented as follows: A method for optimizing the operation of a thermal power plant based on digital twin technology, comprising the following steps:

[0010] Step S1: Obtain the physical mechanism and historical operation data of the generator units in the thermal power plant, and process and store the data;

[0011] Deploy sensor networks and data interfaces to collect real-time unit operating data (such as temperature, pressure, flow rate, power, and emission concentration). Simultaneously, integrate physical mechanism data from design drawings and equipment manuals, as well as operation, maintenance, and fault records from historical databases, to establish a unified data platform. Clean, align, and time-synchronize multi-source heterogeneous data, storing it in the database to provide a data source for modeling.

[0012] Step S2: Establish a digital twin model of the generator unit of the thermal power plant based on the physical mechanism and historical operating data;

[0013] Based on the first principles of thermodynamics and fluid mechanics, simulation models of boilers, steam turbines, and generators are established. Using historical operating data, supplementary models for equipment performance degradation and efficiency changes are trained through machine learning methods. The mechanistic model and the data model are coupled and integrated to construct a digital twin model that can reflect the current real state of the unit. The digital twin model includes a marginal cost calculation sub-model and a dynamic characteristic sub-model.

[0014] Step S3: Call the digital twin model to simulate and calculate the real-time marginal cost of each unit at multiple discrete points within the feasible load range. Combine the adjustable load range and the maximum safe load increase / decrease rate to generate a set of cost capacity parameters for each unit, including real-time marginal cost, adjustable load range and maximum safe load increase / decrease rate.

[0015] In the digital twin model, calculations are performed point by point within the feasible load range of the unit with a fixed step size. At each discrete load point, the marginal cost sub-model is called to calculate its real-time marginal cost, and the dynamic characteristic sub-model is called to obtain its current maximum safe load increase / decrease rate. Combined with the unit's adjustable load upper and lower limits, a dynamic cost-capacity parameter list is generated for each unit.

[0016] Step S4: With the minimum total power generation cost of the power plant as the primary optimization objective, the optimization algorithm is invoked to make load allocation decisions;

[0017] The embedded optimization algorithm is invoked, with the minimum total cost of the entire plant as the main objective function. The inputs are the total load command of the power grid and the cost-capacity parameter list of each unit. At the same time, the algorithm will use the allowable fluctuation range of main steam temperature and pressure, the limit of metal thermal stress and the real-time limit of environmental emission as constraints to calculate a set of load allocation commands that enable all units to operate in a coordinated manner within a safe and economical range.

[0018] Step S5: Perform simulation prediction and security verification based on the digital twin model;

[0019] The optimized load allocation instructions and change trajectories are input into the dynamic characteristic sub-model of the digital twin model for simulation. The system predicts the change curves of key parameters (such as main steam temperature, metal stress, and emissions) over a future period. The system automatically compares the predicted curves with preset safe operating thresholds. If all parameters are within safe limits, the verification is passed; if any parameter exceeds the threshold, an alarm is triggered, and the out-of-limit equipment and parameters are recorded.

[0020] Step S6: Based on the simulation prediction and safety verification results, select and adjust the optimization algorithm and repeat step S4 or issue an execution command.

[0021] If the safety verification passes, the system will directly send optimization instructions to the power plant's distributed control system to drive the physical units to execute.

[0022] If the safety verification fails, the system will automatically adjust the relevant constraints in the optimization algorithm based on the verification results (such as reducing the adjustable load range of the unit and reducing its allowable rate of increase and decrease), and then jump back to step S4 to re-perform the optimization calculation and generate a new load allocation scheme until the safety verification is passed.

[0023] Further preferred: In step S1, the physical mechanism and historical operating data of the generator set include equipment parameters, structural model, real-time status, fault records, maintenance records, efficiency indicators, quality inspection reports and operation logs.

[0024] A further preferred embodiment: In step S2, the digital twin model of the thermal power plant generator unit integrates a marginal cost model and a dynamic characteristic model;

[0025] The marginal cost model is used to calculate the marginal cost of power generation, and the dynamic characteristic model is used to predict the key constraints and maximum safe load change rate of the unit during the load increase and decrease process. The key constraints include the upper and lower limits of unit load, the allowable fluctuation range of main steam temperature and pressure, the limit of metal thermal stress, and the real-time limit of environmental emission.

[0026] A further preferred embodiment: In step S4, the calculation steps of the optimization algorithm include:

[0027] Set an acceptable marginal cost range for each operating unit based on its current operating conditions and real-time health status;

[0028] Generate a load allocation scheme that satisfies the constraint that the operating marginal cost of all units falls within their own acceptable marginal cost range;

[0029] From all load allocation schemes that meet the constraints, select the scheme that minimizes the total power generation cost of the entire plant as the optimized load instruction.

[0030] A further preferred embodiment: the acceptable marginal cost range is [C]. i -Δi,C i +Δi], where C i Δi is the marginal cost benchmark value of the unit under the current operating conditions and target load point, and Δi is the allowable deviation value calculated based on the real-time health status and historical regulation performance of the equipment.

[0031] A further preferred embodiment is that the optimization algorithm is a multi-objective collaborative constant incremental rate algorithm, wherein the optimization objectives of the multi-objective collaborative constant incremental rate algorithm include power grid frequency regulation demand, environmental constraints, fuel prices and equipment health status.

[0032] Further preferred method: In step S5, the execution process of the optimized load command is simulated using a digital twin model to predict the change trajectory of key operating parameters of the generator set. The predicted value is compared with the safe operating threshold. If the predicted value exceeds the limit, an alarm is triggered and the command is frozen.

[0033] A thermal power plant operation optimization system based on digital twin technology, applied to a thermal power plant operation optimization method based on digital twin technology, includes:

[0034] The data collection and processing module is used to acquire the physical mechanism and historical operation data of the generator units in thermal power plants, and to process and store the data.

[0035] The digital twin modeling module is used to establish a digital twin model of the generator unit of a thermal power plant based on the physical mechanism and historical operating data.

[0036] The parameter generation module is used to generate cost capability parameter sets for each unit;

[0037] The algorithm decision module is used to call optimization algorithms to make load allocation decisions;

[0038] The calibration module is used for simulation prediction and safety calibration;

[0039] The execution module is used to select, adjust, and optimize the algorithm based on simulation predictions and safety verification results, and then repeatedly execute S4 or issue execution instructions.

[0040] An electronic device includes: at least one processor; and a memory communicatively connected to the at least one processor;

[0041] The memory stores instructions that can be executed by the at least one processor, which are executed by the at least one processor to enable the at least one processor to perform the operation optimization method for a thermal power plant based on digital twin technology as described in any one of claims 1-7.

[0042] A computer-readable storage medium storing computer instructions for causing a computer to execute a method for optimizing the operation of a thermal power plant based on digital twin technology.

[0043] The embodiments of the present invention have the following advantages due to the adoption of the above technical solutions:

[0044] I. This invention realizes the dynamic transformation of economic dispatch of thermal power plants by establishing a digital twin model linked with the optimization algorithm. The digital twin model is used as the key to optimization calculation. Its output marginal cost and safety boundary are called to assist decision-making, ensuring that the load allocation scheme is not only based on the actual capacity of the units, but also can predict the safety risks in the execution process. This prevents the optimization results from deviating from the actual optimal solution due to model lag, thereby improving the economy and safety of power plant operation.

[0045] Second, this invention achieves adaptive economic scheduling under safety constraints by introducing marginal cost range constraints based on equipment health status and a closed-loop optimization mechanism. By integrating real-time equipment health status and historical adjustment performance for the cost range of each unit, the optimization scheme can adapt to individual differences and performance changes of the units. The invention uses a digital twin model for simulation and safety verification, and automatically adjusts constraints and re-optimizes schemes that are predicted to exceed limits, thereby reducing the safety risks of generator units and achieving a balance between economy and safety.

[0046] Third, the present invention adopts a multi-objective collaborative optimization scheme, which improves the overall operating efficiency of thermal power plants and their adaptability to the power grid.

[0047] The above overview is for illustrative purposes only and is not intended to be limiting in any way. In addition to the illustrative aspects, embodiments, and features described above, further aspects, embodiments, and features of the invention will become readily apparent from the accompanying drawings and the following detailed description. Attached Figure Description

[0048] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0049] Figure 1 This is a flowchart of the method of the present invention. Detailed Implementation

[0050] The embodiments of this disclosure will now be described in detail with reference to the accompanying drawings.

[0051] It should be understood that the following specific examples illustrate the implementation of this disclosure, and those skilled in the art can easily understand other advantages and effects of this disclosure from the content disclosed in this specification. Obviously, the described embodiments are only a part of the embodiments of this disclosure, and not all of them. This disclosure can also be implemented or applied through other different specific implementation methods, and the details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of this disclosure. It should be noted that, in the absence of conflict, the following embodiments and features in the embodiments can be combined with each other. Based on the embodiments in this disclosure, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this disclosure.

[0052] It should be noted that various aspects of embodiments within the scope of the appended claims are described below. It will be apparent that the aspects described herein can be embodied in a wide variety of forms, and any particular structure and / or function described herein is merely illustrative. Based on this disclosure, those skilled in the art will understand that one aspect described herein can be implemented independently of any other aspect, and two or more of these aspects can be combined in various ways. For example, any number of aspects set forth herein can be used to implement the device and / or practice the method. Additionally, this device and / or method can be implemented using structures and / or functionalities other than one or more of the aspects set forth herein.

[0053] It should also be noted that the illustrations provided in the following embodiments are only schematic representations of the basic concept of this disclosure. The drawings only show the components related to this disclosure and are not drawn according to the number, shape and size of the components in actual implementation. In actual implementation, the form, quantity and proportion of each component can be arbitrarily changed, and the layout of the components may also be more complex.

[0054] Furthermore, specific details are provided in the following description to facilitate a thorough understanding of the examples. However, those skilled in the art will understand that the described aspects can be practiced without these specific details.

[0055] like Figure 1 As shown in the figure, this embodiment of the invention provides a method for optimizing the operation of a thermal power plant based on digital twin technology, including the following steps:

[0056] Step S1: Obtain the physical mechanism and historical operation data of the generator set of the thermal power plant, process and store the data. The physical mechanism and historical operation data of the generator set include equipment parameters, structural model, real-time status, fault records, maintenance records, efficiency indicators, quality inspection reports and operation logs.

[0057] The physical mechanisms and historical operating data of the generator set form the data foundation for building a high-fidelity digital twin model. Physical mechanism data refers to the inherent attributes of the unit extracted from design drawings, equipment manuals, and thermal calculation sheets, such as boiler thermal efficiency curves, turbine characteristic curves, and pipeline resistance coefficients. Historical operating data includes real-time sensor data (such as temperature, pressure, flow rate, power, and emission concentration) as well as fault records, maintenance records, efficiency indicators, quality inspection reports, and operation logs from the information system. This data reflects the evolution of the unit's state and performance degradation over time.

[0058] To achieve the fusion of multi-source data, this embodiment adopts a hybrid storage architecture of time-series database and relational database. Real-time streaming data is cleaned, aligned, and time-stamped, and statistical features are extracted. Event-type data is structured and labeled, ultimately forming a unified data platform to provide data sources for subsequent modeling.

[0059] Step S2: Establish a digital twin model of the generator unit of the thermal power plant based on the physical mechanism and historical operation data. The digital twin model of the generator unit of the thermal power plant integrates the marginal cost model and the dynamic characteristic model.

[0060] The marginal cost model is used to calculate the marginal cost of power generation, while the dynamic characteristic model is used to predict the key constraints and maximum safe load change rate of the unit during the load increase and decrease process. The key constraints include the upper and lower limits of the unit load, the allowable fluctuation range of the main steam temperature and pressure, the limit of metal thermal stress, and the real-time limit of environmental emissions.

[0061] The mechanistic model is based on first principles of thermodynamics, fluid mechanics, and rotor dynamics, establishing differential or algebraic equations for sub-processes such as boiler combustion, steam-water system, turbine flow, and generator electromagnetics, forming the deterministic basis of the model.

[0062] The data-driven component addresses issues such as component aging, scaling, and efficiency degradation that are difficult to describe precisely using mechanistic models. It employs neural networks to train historical operating data and establish equipment performance degradation compensation and efficiency correction models.

[0063] By coupling and integrating the above two parts, a digital twin model that can reflect the current real state of the unit is formed. This model integrates two major functional sub-models:

[0064] The marginal cost model is used to calculate the marginal cost of power generation in real time, and its form is as follows:

[0065]

[0066] Among them, MC i Let ΔF be the marginal cost of unit i. i ΔP represents the change in fuel cost. i For power increments, the marginal cost model will take into account factors such as current coal quality, boiler efficiency, and auxiliary power consumption.

[0067] The dynamic characteristic model is used to predict the key constraints and maximum safe load change rate of the unit during the load increase and decrease process. The key constraints include the upper and lower limits of the unit load, the allowable fluctuation range of the main steam temperature and pressure, the limit of metal thermal stress, and the real-time limit of environmental emission. The dynamic characteristic model simulates the load change process and outputs the change trajectory and limit rate of key parameters.

[0068] Step S3: Call the digital twin model to simulate and calculate the real-time marginal cost of each unit at multiple discrete points within the feasible load range. Combine the adjustable load range and the maximum safe load increase / decrease rate to generate a set of cost capacity parameters for each unit, including real-time marginal cost, adjustable load range and maximum safe load increase / decrease rate.

[0069] The system performs a discretized scan of the feasible load range for each unit with a fixed step size (e.g., 1MW), and at each discrete load point P i,j Next, the marginal cost model is invoked to calculate the real-time marginal cost MC at that point. i,j The maximum safe lifting / lowering load rate under this operating condition is obtained by calling the dynamic characteristic model. and adjustable load range[ , The calculation results of all discrete points are integrated to form the cost-capacity parameter set of the unit, the structure of which is as follows:

[0070]

[0071] The parameter set reflects the unit's economic characteristics and regulation capabilities under its current health condition, providing real-time input for subsequent optimization.

[0072] Step S4: With the minimum total power generation cost of the power plant as the primary optimization objective, the optimization algorithm is invoked to make load allocation decisions. The calculation steps of the optimization algorithm include:

[0073] Set an acceptable marginal cost range for each operating unit based on its current operating conditions and real-time health status;

[0074] Generate a load allocation scheme that satisfies the constraint that the operating marginal cost of all units falls within their own acceptable marginal cost range;

[0075] From all load allocation schemes that meet the constraints, select the scheme that minimizes the total power generation cost of the entire plant as the optimized load instruction;

[0076] The acceptable marginal cost range is [C i -Δi,C i +Δi], where C i Δi is the marginal cost benchmark value of the unit under the current operating conditions and target load point, and Δi is the allowable deviation value calculated based on the real-time health status and historical regulation performance of the equipment. The optimization algorithm is a multi-objective collaborative equal incremental rate algorithm. The optimization objectives of the multi-objective collaborative equal incremental rate algorithm include grid frequency regulation demand, environmental constraints, fuel prices and equipment health status.

[0077] The expressions for the multi-objective cooperative incremental rate algorithm and core constraints are as follows:

[0078]

[0079]

[0080] in, It is the real-time marginal cost of unit i at output P, ​​dynamically calculated by the digital twin model, and the integral represents the cost from the current output. Adjust to target output The accumulated changes in fuel costs reflect the dispatch principle of prioritizing economic efficiency and pursuing the lowest possible power generation cost for the entire plant.

[0081] The core constraints include power balance constraints, upper and lower limits of unit output constraints, load increase and decrease rate constraints, marginal cost range constraints, and environmental emission constraints.

[0082] The algorithm aims to minimize the total cost increase from adjusting the output of all units, thereby achieving optimal economic benefits for the entire plant.

[0083] The algorithm first solves for the set of load allocation schemes that satisfy all constraints, and then selects the scheme that minimizes the total power generation cost of the power plant as the optimized load command.

[0084] Step S5: Perform simulation prediction and safety verification based on the digital twin model. Use the digital twin model to simulate the execution process of the optimized load command, predict the change trajectory of the key operating parameters of the generator set, compare the predicted value with the safe operation threshold, and trigger an alarm and freeze the command if the predicted value exceeds the limit.

[0085] A proactive safety check is performed before the load command is issued. The specific process is as follows:

[0086] The optimized load command and its change trajectory are input into the dynamic characteristic model for closed-loop simulation to predict the change curves of key operating parameters within a future period T. The system compares the predicted values ​​with the preset safe operating thresholds. If any parameter exceeds the threshold, an alarm is immediately triggered and the current optimized command is frozen to prevent unsafe commands from being issued. At the same time, the equipment, parameters and time points that exceed the limits are recorded to provide a basis for subsequent constraint adjustments.

[0087] Step S6: Based on the simulation prediction and safety verification results, select and adjust the optimization algorithm and repeat step S4 or issue an execution command.

[0088] If the safety verification passes, the system will send optimization instructions to the power plant's distributed control system (DCS) via a standard communication protocol (such as OPCUA) to drive the physical units to execute and complete the optimization.

[0089] If the safety check fails, the system automatically adjusts the relevant constraints in the optimization algorithm based on the check results. For example, it may narrow the adjustable load range of the unit or reduce its maximum allowable load increase / decrease rate. After adjustment, the system automatically returns to step S4 to recalculate the optimization based on the new constraints, generating a feasible load allocation scheme. This process can be iterated until the optimal solution that passes the safety check is obtained.

[0090] This invention establishes a digital twin model linked with the optimization algorithm, enabling dynamic transformation of economic dispatch in thermal power plants. The digital twin model is used as the key to optimization calculation, and its output marginal cost and safety boundary are used to assist decision-making. This ensures that the load allocation scheme is not only based on the actual capacity of the units, but also can predict the safety risks during the execution process, preventing the optimization results from deviating from the actual optimal solution due to model lag, and improving the economy and safety of power plant operation.

[0091] This invention achieves adaptive economic scheduling under safety constraints by introducing marginal cost range constraints based on equipment health status and a closed-loop optimization mechanism. By integrating real-time equipment health status and historical regulation performance into the cost range of each unit, the optimization scheme can adapt to individual differences and performance changes of the units. The invention uses a digital twin model for simulation and safety verification, automatically adjusts constraints and re-optimizes schemes that are predicted to exceed limits, thereby reducing the safety risks of generator units and achieving a balance between economy and safety.

[0092] This invention employs a multi-objective collaborative optimization scheme to improve the overall operational efficiency of thermal power plants and their adaptability to the power grid.

[0093] Example 2

[0094] A thermal power plant operation optimization system based on digital twin technology, applied to a thermal power plant operation optimization method based on digital twin technology, includes:

[0095] The data collection and processing module is used to acquire physical mechanism and historical operating data of generator units in thermal power plants, process and store the data as the foundation of the system data. Through industrial IoT gateways and standard interfaces, the module collects multi-source sensor data from the entire plant's DCS, SIS, and other systems in real time, while integrating physical mechanism data from design drawings, equipment manuals, and historical operation and maintenance records. The module performs data cleaning, time-stamp alignment, and storage, providing a standardized database for the upper-level model.

[0096] The digital twin modeling module is used to build digital twin models of generator units in thermal power plants based on physical mechanisms and historical operating data. This module employs a hybrid modeling paradigm combining mechanistic models and data-driven approaches. It constructs a deterministic kernel based on first principles of thermodynamics and fluid mechanics, and utilizes machine learning algorithms to compensate for time-varying characteristics such as equipment aging and performance degradation. The model integrates a marginal cost sub-model and a dynamic characteristic sub-model, and is continuously updated through an online learning mechanism to ensure synchronization between the virtual model and the physical entity.

[0097] The parameter generation module is used to generate cost capability parameter sets for each unit. The parameter generation module drives the digital twin model to perform virtual frequency sweep test, and performs discretization calculation on the feasible load range of each unit with a fixed step size. It calls the twin model to calculate the real-time marginal cost and maximum safe load increase / decrease rate at each discrete load point, and generates cost capability parameter sets to replace the traditional static design curve.

[0098] The algorithm decision-making module is used to invoke optimization algorithms to make load allocation decisions. The primary objective of this module is to minimize the total plant cost, and it uses power balance, unit output limits, regulation rate, and environmental emissions as hard constraints. It also introduces marginal cost range constraints based on equipment health status, allowing units to operate differentiatedly within a reasonable range. Using dynamic inputs provided by the parameter generation module, it solves for a preliminary optimal load allocation scheme considering safety, environmental protection, and economic factors.

[0099] The calibration module is used for simulation prediction and safety calibration. Before the instruction is issued, the calibration module loads the optimized load instruction output by the algorithm decision module into the digital twin dynamic model, performs simulation, and predicts the change trajectory of key operating parameters in the future. The system automatically compares the predicted value with the dynamic safety threshold. Once the risk of exceeding the limit is found, an alarm is immediately triggered and the instruction is frozen.

[0100] The execution module is used to select and adjust the optimization algorithm and repeat step S4 or issue an execution command based on the simulation prediction and safety verification results. The execution module executes branch logic according to the results of the verification module: if the safety verification passes, the optimization command is safely issued to the power plant's distributed control system for execution through the standard protocol; if the verification fails, the relevant constraints in the algorithm decision module are automatically adjusted based on the diagnostic information, and a new round of iterative optimization calculation is triggered until a safe and feasible optimal solution is generated.

[0101] Example 3

[0102] An electronic device includes: at least one processor; and a memory communicatively connected to the at least one processor;

[0103] The memory stores instructions that can be executed by at least one processor, which enables the at least one processor to execute a method for optimizing the operation of a thermal power plant based on digital twin technology.

[0104] A computer-readable storage medium storing computer instructions for causing a computer to execute a method for optimizing the operation of a thermal power plant based on digital twin technology.

[0105] An electronic device according to embodiments of this disclosure includes a memory and a processor. The memory is used to store non-transitory computer-readable instructions. Specifically, the memory may include one or more computer program products, which may include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. The volatile memory may, for example, include random access memory (RAM) and / or cache memory. The non-volatile memory may, for example, include read-only memory (ROM), a hard disk, flash memory, etc.

[0106] The processor may be a central processing unit (CPU) or other processing unit with data processing and / or instruction execution capabilities, and may control other components in the electronic device to perform desired functions. In one embodiment of this disclosure, the processor is used to execute computer-readable instructions stored in the memory, causing the electronic device to perform all or part of the steps of the aforementioned embodiments of this disclosure for optimizing the operation of a thermal power plant based on digital twin technology.

[0107] It should be noted that the various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. The same or similar parts between the various embodiments can be referred to each other.

[0108] In this disclosure, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. The block diagrams of devices, apparatuses, devices, and systems involved in this disclosure are merely illustrative examples and are not intended to require or imply that they must be connected, arranged, or configured in the manner shown in the block diagrams. As those skilled in the art will recognize, these devices, apparatuses, devices, and systems can be connected, arranged, and configured in any manner. Words such as "comprising," "including," "having," etc., are open-ended terms meaning "including but not limited to," and are used interchangeably with them. The terms "or" and "and" as used herein refer to the terms "and / or," and are used interchangeably with them unless the context clearly indicates otherwise. The term "such as" as used herein refers to the phrase "such as but not limited to," and is used interchangeably with it.

[0109] It should also be noted that in the system disclosed herein, the components or steps can be decomposed and / or recombined. These decompositions and / or recombinations should be considered as equivalent solutions to this disclosure.

[0110] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any person skilled in the art can easily conceive of various variations or substitutions within the technical scope disclosed in the present invention, and these should all be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A method for optimizing the operation of a thermal power plant based on digital twin technology, characterized in that, Includes the following steps: Step S1: Obtain the physical mechanism and historical operation data of the generator units in the thermal power plant, and process and store the data; Step S2: Establish a digital twin model of the generator unit of the thermal power plant based on the physical mechanism and historical operating data; Step S3: Call the digital twin model to simulate and calculate the real-time marginal cost of each unit at multiple discrete points within the feasible load range. Combine the adjustable load range and the maximum safe load increase / decrease rate to generate a set of cost capacity parameters for each unit, including real-time marginal cost, adjustable load range and maximum safe load increase / decrease rate. Step S4: With the minimum total power generation cost of the power plant as the primary optimization objective, the optimization algorithm is invoked to make load allocation decisions; Step S5: Perform simulation prediction and security verification based on the digital twin model; Step S6: If the simulation prediction and safety verification results are normal, then issue an execution command; otherwise, adjust the optimization algorithm and repeat step S4.

2. The method for optimizing the operation of a thermal power plant based on digital twin technology according to claim 1, characterized in that, In step S1, the physical mechanism and historical operating data of the generator set include equipment parameters, structural model, real-time status, fault records, maintenance records, efficiency indicators, quality inspection reports and operation logs.

3. The method for optimizing the operation of a thermal power plant based on digital twin technology according to claim 1, characterized in that, In step S2, the digital twin model of the thermal power plant generator unit integrates a marginal cost model and a dynamic characteristic model; The marginal cost model is used to calculate the marginal cost of power generation, and the dynamic characteristic model is used to predict the key constraints and maximum safe load change rate of the unit during the load increase and decrease process. The key constraints include the upper and lower limits of unit load, the allowable fluctuation range of main steam temperature and pressure, the limit of metal thermal stress, and the real-time limit of environmental emission.

4. The method for optimizing the operation of a thermal power plant based on digital twin technology according to claim 1, characterized in that, In step S4, the calculation steps of the optimization algorithm include: Set a marginal cost range for each operating unit based on its current operating conditions and real-time health status; Generate a load allocation scheme that satisfies the constraint that the operating marginal cost of all units falls within their own acceptable marginal cost range; From all load allocation schemes that meet the constraints, select the scheme that minimizes the total power generation cost of the entire plant as the optimized load instruction.

5. The method for optimizing the operation of a thermal power plant based on digital twin technology according to claim 4, characterized in that, The acceptable marginal cost range is [C]. i -Δi,C i +Δi], where C i Δi is the marginal cost benchmark value of the unit under the current operating conditions and target load point, and Δi is the allowable deviation value calculated based on the real-time health status and historical regulation performance of the equipment.

6. The method for optimizing the operation of a thermal power plant based on digital twin technology according to claim 4, characterized in that, The optimization algorithm is a multi-objective collaborative constant incremental rate algorithm, and the optimization objectives of the multi-objective collaborative constant incremental rate algorithm include power grid frequency regulation demand, environmental constraints, fuel prices and equipment health status.

7. The method for optimizing the operation of a thermal power plant based on digital twin technology according to claim 1, characterized in that, In step S5, the execution process of the optimized load command is simulated using a digital twin model to predict the change trajectory of key operating parameters of the generator set. The predicted values ​​are compared with the safe operating thresholds. If the predicted values ​​exceed the limits, an alarm is triggered and the command is frozen.

8. A thermal power plant operation optimization system based on digital twin technology, applied to the thermal power plant operation optimization method based on digital twin technology as described in any one of claims 1-7, characterized in that, include: The data collection and processing module is used to acquire the physical mechanism and historical operation data of the generator units in thermal power plants, and to process and store the data. The digital twin modeling module is used to establish a digital twin model of the generator unit of a thermal power plant based on the physical mechanism and historical operating data. The parameter generation module is used to generate cost capability parameter sets for each unit; The algorithm decision module is used to call optimization algorithms to make load allocation decisions; The calibration module is used for simulation prediction and safety calibration; The execution module is used to select whether to issue execution instructions or repeatedly optimize the algorithm based on simulation predictions and safety verification results.

9. An electronic device, characterized in that, The electronic device includes: at least one processor; and a memory communicatively connected to the at least one processor; The memory stores instructions that can be executed by the at least one processor, which are executed by the at least one processor to enable the at least one processor to perform the operation optimization method for a thermal power plant based on digital twin technology as described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions for causing a computer to perform a method for optimizing the operation of a thermal power plant based on digital twin technology as described in any one of claims 1-7.

Images