Method, device and system for optimizing control strategy of gas turbine

Abstract

The invention relates to a control strategy optimization method, device and system for a gas turbine, and relates to the technical field of gas turbines. The method comprises the following steps: respectively controlling a gas turbine entity and a twin model by adopting a first control strategy to obtain a first execution result and a second execution result; determining a first operation deviation degree according to the first execution result and the second execution result; under the condition that the first operation deviation degree does not meet the preset condition, correcting model parameters of the twin model; under the condition that the first operation deviation degree meets a preset condition, the gas turbine entity is controlled through the first control strategy, the twin model is controlled through the second control strategy, and a third execution result and a fourth execution result are obtained; determining a second operation deviation degree according to the third execution result and the fourth execution result; and adjusting the second control strategy under the condition that the second operation deviation degree does not meet the preset condition. According to the scheme, the accuracy of optimizing the gas control strategy is improved.

Description

Technical Field

[0001] The present disclosure relates to the technical field of gas turbines, and in particular to a control strategy optimization method, device and system for a gas turbine. Background Art

[0002] In the related technology, in order to enable the gas turbine to have better peak load regulation capability, it is necessary to formulate a reasonable control strategy for the gas turbine. After formulating the control strategy for the gas turbine, it is necessary to test the control strategy. Only after passing the test can it be applied to the gas turbine control system. At present, the control strategy is usually tested offline, which is out of the actual operating environment of the gas turbine, resulting in the inability to fully detect the defects of the control strategy. Summary of the invention

[0003] In order to overcome the problems existing in the related art, the present disclosure provides a control strategy optimization method, device and system for a gas turbine.

[0004] According to a first aspect of an embodiment of the present disclosure, a control strategy optimization method for a gas turbine is provided, comprising:

[0005] Using a first control strategy to respectively control a gas turbine entity and a twin model corresponding to the gas turbine entity to execute a target task, and obtaining a first execution result of the gas turbine entity and a second execution result of the twin model;

[0006] Determining a first operating deviation degree between the twin model and the gas turbine entity according to the first execution result and the second execution result;

[0007] In the case where the first operation deviation degree does not meet the preset conditions, the model parameters of the twin model are corrected, and the step of using the first control strategy to respectively control the gas turbine entity and the twin model corresponding to the gas turbine entity to perform the target task is returned to execution;

[0008] When the first operation deviation degree meets the preset condition, the first control strategy is adopted to control the gas turbine entity to perform the target task, and the second control strategy is adopted to control the twin model to perform the target task, so as to obtain a third execution result of the gas turbine entity and a fourth execution result of the twin model;

[0009] Determining a second operation deviation degree between the twin model and the gas turbine entity according to the third execution result and the fourth execution result;

[0010] When the second operating deviation degree does not meet the preset conditions, adjust the second control strategy and return to the step of using the first control strategy to control the gas turbine entity to perform the target task and using the second control strategy to control the twin model to perform the target task until the second operating deviation degree meets the preset conditions and the second control strategy is determined as the optimized control strategy.

[0011] In some embodiments of the present disclosure, the first execution result includes first operating data of the gas turbine entity during the execution of the target task, and the second execution result includes second operating data of the twin model during the execution of the target task;

[0012] The determining, according to the first execution result and the second execution result, a first operation deviation degree between the twin model and the gas turbine entity comprises:

[0013] Calculating a first steady-state deviation value between the gas turbine entity and the twin model according to the first operating data and the second operating data;

[0014] Calculating a first dynamic deviation value between a gas turbine entity and a twin model according to the first operating data and the second operating data;

[0015] After determining the first operation deviation degree between the twin model and the gas turbine entity according to the first execution result and the second execution result, the method further includes:

[0016] When the first steady-state deviation value is greater than a first preset threshold value and / or the first dynamic deviation value is greater than a second preset threshold value, it is determined that the first operation deviation degree does not meet a preset condition.

[0017] In some embodiments of the present disclosure, when the first operation deviation degree does not meet a preset condition, correcting the model parameters of the twin model includes:

[0018] When the first operation deviation degree does not meet the preset condition, an extended Kalman filter algorithm is used to determine the model parameter correction value of the twin model;

[0019] The model parameters of the twin model are corrected according to the model parameter correction values.

[0020] In some embodiments of the present disclosure, the third execution result includes third operating data of the gas turbine entity in the process of executing the target task, and the fourth execution result includes fourth operating data of the twin model in the process of executing the target task;

[0021] Determining a second operation deviation degree between the twin model and the gas turbine entity according to the third execution result and the fourth execution result includes:

[0022] Calculating a second steady-state deviation value between the gas turbine entity and the twin model according to the third operating data and the fourth operating data;

[0023] Calculating a second dynamic deviation value between the gas turbine entity and the twin model according to the third operating data and the fourth operating data;

[0024] After determining the second operation deviation degree between the twin model and the gas turbine entity according to the third execution result and the fourth execution result, the method further includes:

[0025] When the second steady-state deviation value is greater than a third preset threshold and / or the second dynamic deviation value is greater than a fourth preset threshold, it is determined that the second operation deviation degree does not meet a preset condition.

[0026] In some embodiments of the present disclosure, the adopting of the first control strategy to respectively control the gas turbine entity and the twin model corresponding to the gas turbine entity to perform the target task, and obtaining the first execution result of the gas turbine entity and the second execution result of the twin model, includes:

[0027] Using a closed-loop control method, according to the first control strategy, the gas turbine entity is controlled to perform the target task, and the first execution result is obtained;

[0028] An open-loop control method is adopted to control the twin model to execute the target task according to the first control strategy to obtain the second execution result.

[0029] In some embodiments of the present disclosure, the method further includes:

[0030] Acquiring operating environment information of the gas turbine entity in real time;

[0031] Update the operating environment parameters of the twin model according to the operating environment information.

[0032] According to a second aspect of an embodiment of the present disclosure, a control strategy optimization device for a gas turbine is provided, comprising:

[0033] A first execution unit, configured to respectively control the gas turbine entity and the twin model corresponding to the gas turbine entity to execute a target task by adopting a first control strategy, and obtain a first execution result of the gas turbine entity and a second execution result of the twin model;

[0034] A first determining unit, configured to determine a first operating deviation degree between the twin model and the gas turbine entity according to the first execution result and the second execution result;

[0035] A correction unit, configured to correct the model parameters of the twin model when the first operation deviation degree does not meet the preset conditions, and return to the step of using the first control strategy to respectively control the gas turbine entity and the twin model corresponding to the gas turbine entity to perform the target task;

[0036] A first execution unit is used to control the gas turbine entity to perform the target task by adopting the first control strategy, and to control the twin model to perform the target task by adopting the second control strategy, when the first operation deviation degree meets a preset condition, to obtain a third execution result of the gas turbine entity and a fourth execution result of the twin model;

[0037] A second determining unit, configured to determine a second operation deviation degree between the twin model and the gas turbine entity according to the third execution result and the fourth execution result;

[0038] An adjustment unit is used to adjust the second control strategy when the second operating deviation degree does not meet the preset conditions, return to the steps of using the first control strategy to control the gas turbine entity to perform the target task, and use the second control strategy to control the twin model to perform the target task, until the second operating deviation degree meets the preset conditions, and determine the second control strategy as the control strategy to complete the optimization.

[0039] According to a third aspect of an embodiment of the present disclosure, an electronic device includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the method described in any one of the first aspects is implemented.

[0040] According to a fourth aspect of an embodiment of the present disclosure, there is provided a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the method according to any one of the first aspects is implemented.

[0041] According to a fifth aspect of an embodiment of the present disclosure, a computer program product is provided, comprising a computer program, wherein the computer program implements the method as described in any one of the first aspects when executed by a processor.

[0042] The technical solution provided by the embodiments of the present disclosure may include the following beneficial effects: by continuously correcting the twin model according to the degree of operating deviation between the gas turbine entity and the twin model, the deviation between the twin model and the gas turbine entity is reduced, thereby improving the realism of utilizing the twin model, and further improving the accuracy of verifying the control effect of the control strategy; in addition, by controlling the gas turbine entity and the corrected twin model to execute different control strategies, the operating effect deviation between the execution of different control strategies is obtained, and the second control strategy to be optimized is adjusted according to the degree of deviation, thereby improving the accuracy of optimizing the second control strategy.

[0043] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.

[0045] Figure 1 The present invention is a flow chart of a method for optimizing a control strategy of a gas turbine according to an exemplary embodiment.

[0046] Figure 2 It is a structural block diagram of a lightweight gas turbine control strategy online verification system according to an exemplary embodiment.

[0047] Figure 3 It is a block diagram of a control strategy optimization device for a gas turbine according to an exemplary embodiment.

[0048] Figure 4 The invention is a block diagram of a device for a control strategy optimization method for a gas turbine according to an exemplary embodiment. DETAILED DESCRIPTION

[0049] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present invention. Instead, they are merely examples of devices and methods consistent with some aspects of the present invention as detailed in the appended claims.

[0050] The terms used in the disclosed embodiments are only for the purpose of describing specific embodiments, and are not intended to limit the disclosed embodiments. The singular forms "a", "an" and "the" used in the disclosed embodiments and the appended claims are also intended to include plural forms, unless the context clearly indicates other meanings.

[0051] It should be understood that although the terms first, second, third, etc. may be used to describe various information in the disclosed embodiments, these information should not be limited to these terms. These terms are only used to distinguish the same type of information from each other. For example, without departing from the scope of the disclosed embodiments, the first information may also be referred to as the second information, and similarly, the second information may also be referred to as the first information. Depending on the context, the words "if" and "if" as used herein may be interpreted as "at" or "when" or "in response to determination".

[0052] In addition, various forms of processes shown in the embodiments of the present disclosure may be used to reorder, add or delete steps. For example, the steps described in the present application may be performed in parallel, sequentially or in different orders, as long as the desired results of the technical solution disclosed in the present disclosure can be achieved, and this document does not limit this.

[0053] In the related technologies, gas turbine power generation is an important peak-shaving means in the power industry. With the requirements of carbon peak and carbon neutrality, however, since new energy power generation is greatly affected by natural environment factors and the development of energy storage technology is slow, the demand for gas turbine peak-shaving capacity will inevitably increase in the process of new energy power generation development. Gas turbines will play an important role in the country's realization of carbon peak and carbon neutrality. Once the gas turbine is loaded with the base load, it will become a peak power generation asset. To dispatch faster starting and loading requirements and adjust the load multiple times within an hour, the gas turbine control system must survive rapid frequency and load transients and must also comply with strict environmental regulations. Rapid grid frequency or load transients, changes in environmental conditions, fuel quality, and component degradation all place higher requirements on gas turbine control. Therefore, it is necessary to study more advanced gas turbine control strategies to solve the current gas turbine control problems and support the research on advanced gas turbine control systems. After completing the research and development of advanced gas turbine control strategies, the studied control strategies need to be tested comprehensively, and they can only be applied to gas turbine control systems after passing the tests.

[0054] Currently, the control strategy is usually tested offline, which is out of the actual operating environment of the gas turbine and results in the inability to fully detect the defects of the control strategy.

[0055] In order to solve the above problems, the present invention provides a control strategy optimization method, device and system for a gas turbine. By continuously correcting the twin model according to the degree of operating deviation between the gas turbine entity and the twin model, the deviation between the twin model and the gas turbine entity is reduced, thereby improving the realism of using the twin model, and then improving the accuracy of verifying the control effect of the control strategy. In addition, by controlling the gas turbine entity and the corrected twin model to execute different control strategies, the operating effect deviation between the execution of different control strategies is obtained, and the second control strategy to be optimized is adjusted according to the degree of deviation, thereby improving the accuracy of optimizing the second control strategy.

[0056] Figure 1 is a flow chart of a control strategy optimization method for a gas turbine according to an exemplary embodiment. Figure 1 As shown, it should be noted that the control strategy optimization method for a gas turbine according to the embodiment of the present disclosure is applied to a control strategy optimization device for a gas turbine. Figure 1 As shown, the method may include the following steps:

[0057] Step 101: adopt a first control strategy to respectively control a gas turbine entity and a twin model corresponding to the gas turbine entity to execute a target task, and obtain a first execution result of the gas turbine entity and a second execution result of the twin model.

[0058] It can be understood that in order to determine the gap between the twin model and the gas turbine entity, the first control strategy can be used to control the gas turbine entity and perform the same target task with the twin model to obtain different execution results after the twin model and the gas turbine entity execute the same control strategy.

[0059] As an example, the first execution result may include the operating data generated by the gas turbine entity during the execution of the target task according to the first control strategy, as well as the execution result data after completing the target task; the second execution result may include the operating data generated by the twin model during the execution of the target task according to the first control strategy, as well as the execution result data after completing the target task.

[0060] It should be noted that the twin model can be established according to the scope of control strategy verification. For example, if only the control logic of the gas turbine main engine is verified, only the gas turbine main engine model needs to be established; if only the control logic of the gas turbine auxiliary system is verified, only the corresponding auxiliary system model of the gas turbine needs to be established. Modeling can use comprehensive modeling methods such as mechanism modeling, data-driven modeling, and logic modeling to establish a digital twin model.

[0061] In one embodiment, the first control strategy may be a control strategy after optimization.

[0062] In some embodiments of the present disclosure, step 101 may specifically include the following steps:

[0063] Using a closed-loop control method, the gas turbine entity is controlled to perform a target task according to a first control strategy to obtain a first execution result;

[0064] An open-loop control method is adopted to control the twin model to execute the target task according to the first control strategy to obtain the second execution result.

[0065] It can be understood that in order to make the parameters of the twin model as close as possible to the parameters of the gas turbine entity, it is necessary to control the operation process of the gas turbine entity to be the desired operation process. Therefore, for the gas turbine entity, it is necessary to adopt a closed-loop control method to perform the target task, that is, when the first execution result does not meet the preset requirements, it is necessary to continue to execute the first control strategy until the first execution result meets the preset requirements. And, for the twin model, it is necessary to adopt an open-loop control method to perform the target task, that is, only execute the first control strategy once to obtain the second execution result, so that the first execution result that meets the requirements can be compared with the second execution result to determine the gap between the parameters of the twin model and the gas turbine entity.

[0066] Step 102: Determine a first operating deviation degree between the twin model and the gas turbine entity according to the first execution result and the second execution result.

[0067] In one embodiment, the first operating deviation level may include a first steady-state deviation value and / or a first dynamic deviation value.

[0068] For example, the first execution result and the second execution result may both include operating data such as power, compressor outlet temperature, compressor outlet pressure, turbine outlet temperature, and rotation speed.

[0069] In some embodiments of the present disclosure, the first execution result includes first operating data of the gas turbine entity during the execution of the target task, and the second execution result includes second operating data of the twin model during the execution of the target task. Step 102 may specifically include the following steps:

[0070] Calculating a first steady-state deviation value between the gas turbine entity and the twin model based on the first operating data and the second operating data;

[0071] A first dynamic deviation value between the gas turbine entity and the twin model is calculated based on the first operating data and the second operating data.

[0072] In one embodiment, the first steady-state deviation value may be calculated in the following manner:

[0073] First, it is determined whether the operating state of the gas turbine entity is in a steady-state condition. When the gas turbine is connected to the grid, if the change of the actual power of the gas turbine within a certain period is less than the threshold value δ, it is determined to be in a steady-state condition, and the steady-state deviation can be calculated.

[0074]

[0075] in, is the unit power value of the gas turbine entity at the i-th moment; is the power value of the gas turbine unit at the time i+2n; n is the interval parameter for determining the physical operating state of the gas turbine, which can be selected as 10; δ is the steady-state determination threshold, and the control dead zone of the gas turbine power control loop is usually 0.5, so δ can be 1; Go is the grid-connected signal; is the actual power value of the gas turbine at the i+nth moment; is the power calculation value of the twin model at the i+nth moment; e s _P is the power steady-state deviation; is the gas turbine outlet temperature at the moment i+n; is the calculated value of the turbine outlet temperature of the twin model at the i+nth moment; e s _T 4 is the steady-state deviation of turbine outlet temperature.

[0076] In one embodiment, the first dynamic deviation value is calculated in the following manner:

[0077] When the following conditions are met, it is considered to be in dynamic condition:

[0078] or

[0079] in, is the unit speed value of the gas turbine entity at the i-th moment; is the unit speed value of the gas turbine entity at the i+2nth moment; δ 2 is the speed dynamic judgment threshold, which can be 6.

[0080] The calculation method of the first dynamic deviation is the same as the calculation method of the first steady-state deviation.

[0081] After step 102, the method further includes: when the first steady-state deviation value is greater than a first preset threshold value and / or the first dynamic deviation value is greater than a second preset threshold value, determining that the first operating deviation degree does not meet a preset condition.

[0082] It can be understood that when the first steady-state deviation value is greater than the first preset threshold and / or the first dynamic deviation value is greater than the second preset threshold, it means that there is a large gap between the twin model and the gas turbine entity, and the twin model needs to be adjusted.

[0083] Step 103, when the first operating deviation degree does not meet the preset conditions, correct the model parameters of the twin model and return to the step of using the first control strategy to respectively control the gas turbine entity and the twin model corresponding to the gas turbine entity to perform the target task.

[0084] In one embodiment, in order to ensure that the twin model and the gas turbine entity have high accuracy, a gas turbine twin model adaptive correction method is adopted. According to the deviation between the digital twin model and the key parameters of the gas turbine entity, the extended Kalman filter method is adopted to obtain the twin model correction parameters, which may include the compressor flow characteristic correction coefficient, the compressor efficiency characteristic correction coefficient, the combustion chamber efficiency correction coefficient, the combustion chamber pressure drop correction coefficient, the turbine flow characteristic correction coefficient, the turbine efficiency characteristic correction coefficient, the turbine cooling extraction flow correction coefficient, the mechanical efficiency correction coefficient, etc. The correction coefficient will be updated to the gas turbine model correction parameter data container and then deployed to the gas turbine control system twin device.

[0085] In some embodiments of the present disclosure, when the first running deviation degree does not meet the preset conditions, correcting the model parameters of the twin model includes:

[0086] When the first running deviation degree does not meet the preset conditions, the extended Kalman filter algorithm is used to determine the model parameter correction value of the twin model;

[0087] The model parameters of the twin model are corrected according to the model parameter correction values.

[0088] In other embodiments of the present disclosure, when the first operating deviation degree does not meet the preset conditions, an optimal estimation algorithm such as the least squares method may be used to dynamically determine the model parameter correction value according to the first operating deviation degree.

[0089] Step 104, when the first operating deviation degree meets the preset conditions, the first control strategy is adopted to control the gas turbine entity to perform the target task, and the second control strategy is adopted to control the twin model to perform the target task, so as to obtain the third execution result of the gas turbine entity and the fourth execution result of the twin model.

[0090] It can be understood that the purpose of modifying the twin model is to enable the twin model to simulate the gas turbine entity more realistically, thereby more realistically simulating the gas turbine entity to execute the second control strategy to be optimized, and then effectively optimizing the second control strategy.

[0091] Therefore, when the first operating deviation degree meets the preset conditions, the first control strategy is adopted to control the gas turbine entity to perform the target task, and the second control strategy is adopted to control the twin model to perform the target task, so as to obtain the third execution result of the gas turbine entity and the fourth execution result of the twin model. That is, when the twin model can accurately simulate the gas turbine entity, different control strategies are used to perform the same target task, so as to verify whether the second control strategy to be optimized can achieve the same effect as the first control strategy.

[0092] Step 105: Determine a second operation deviation degree between the twin model and the gas turbine entity according to the third execution result and the fourth execution result.

[0093] In some embodiments of the present disclosure, the second operating deviation level may include a second steady-state deviation value and / or a second dynamic deviation value.

[0094] In some embodiments of the present disclosure, the third execution result includes third operating data of the gas turbine entity in the process of performing the target task, and the fourth execution result includes fourth operating data of the twin model in the process of performing the target task. Step 105 may specifically include the following steps:

[0095] Calculating a second steady-state deviation value between the gas turbine entity and the twin model based on the third operating data and the fourth operating data;

[0096] A second dynamic deviation value between the gas turbine entity and the twin model is calculated based on the third operating data and the fourth operating data.

[0097] In the embodiments of the present disclosure, the calculation method of the second steady-state deviation value is the same as the calculation method of the first steady-state deviation value proposed in some embodiments of the present disclosure, and will not be repeated here; the calculation method of the second dynamic deviation value is the same as the calculation method of the first dynamic deviation value proposed in some embodiments of the present disclosure, and will not be repeated here.

[0098] After step 105, the method further includes: when the second steady-state deviation value is greater than a third preset threshold value and / or the second dynamic deviation value is greater than a fourth preset threshold value, determining that the second operating deviation degree does not meet the preset condition.

[0099] It can be understood that when the second steady-state deviation value is greater than the third preset threshold and / or the second dynamic deviation value is greater than the fourth preset threshold, it means that there is a large gap between the execution effect of the second control strategy and the execution effect of the first control strategy, and the second control strategy needs to be optimized.

[0100] It should be noted that the third preset threshold and the fourth preset threshold are both greater than 0, that is, when the second steady-state deviation value is greater than the third preset threshold and / or the second dynamic deviation value is greater than the fourth preset threshold, a positive deviation occurs, and the positive deviation is large enough, indicating that the control effect of the second control strategy is significantly improved compared with the first control strategy;

[0101] In addition, if the second steady-state deviation value is greater than or equal to 0 and less than the third preset threshold, it means that the second control strategy is not significantly improved relative to the first control strategy, and the optimization operation can continue; similarly, if the second dynamic deviation value is greater than or equal to 0 and less than the fourth preset threshold, it means that the second control strategy is not significantly improved relative to the first control strategy, and the optimization operation can continue;

[0102] In addition, if the second steady-state deviation value is less than 0 and / or the second dynamic deviation value is less than 0, a negative deviation occurs, that is, the second control strategy does not achieve the effect of the first control strategy. In this case, the gas turbine operating point where the deviation occurs can be recorded, and the reasons for the deviation are analyzed for each operating point, and the second control strategy is corrected based on the above reasons.

[0103] Step 106, when the second operating deviation degree does not meet the preset conditions, adjust the second control strategy, return to the step of using the first control strategy to control the gas turbine entity to perform the target task, and use the second control strategy to control the twin model to perform the target task, until the second operating deviation degree meets the preset conditions, and determine the second control strategy as the control strategy to complete the optimization.

[0104] In some embodiments of the present disclosure, in order to ensure the effectiveness of the gas turbine control strategy, verification work of the gas turbine control strategy can be performed regularly and switched alternately so that the verification work is performed in a twin model test environment with a higher confidence level.

[0105] In some embodiments of the present disclosure, the method may further include the following steps:

[0106] Obtain the operating environment information of the gas turbine entity in real time;

[0107] Update the operating environment parameters of the twin model according to the operating environment information.

[0108] It can be understood that by acquiring the operating environment information of the gas turbine entity in real time and updating the operating environment parameters of the twin model according to the operating environment information, the twin model can better simulate the operating status of the gas turbine entity and improve the accuracy of verifying the operating effect of the second control strategy.

[0109] In one example, the operating environment parameters may include parameters such as ambient temperature, ambient pressure, atmospheric humidity, etc., and measurement signals of the gas turbine entity may be acquired through a real-time network.

[0110] According to the control strategy optimization method for a gas turbine proposed in the embodiment of the present disclosure, the twin model is continuously corrected according to the degree of operating deviation between the gas turbine entity and the twin model, thereby reducing the deviation between the twin model and the gas turbine entity, thereby improving the fidelity of using the twin model, and further improving the accuracy of verifying the control effect of the control strategy. In addition, by controlling the gas turbine entity and the corrected twin model to execute different control strategies, the operating effect deviation between executing different control strategies is obtained, and the second control strategy to be optimized is adjusted according to the degree of deviation, thereby improving the accuracy of optimizing the second control strategy. In addition, the control strategy optimization method for a gas turbine proposed in the embodiment of the present disclosure continuously corrects the twin model according to the degree of operating deviation between the gas turbine entity and the twin model, thereby realizing lightweight simulation testing under the premise of ensuring the fidelity of the twin model, that is, compared with the semi-physical simulation test method in the prior art, the degree of lightweight is higher under the premise of ensuring the same degree of fidelity, and the cost is effectively reduced.

[0111] Figure 2 is a structural block diagram of an online verification system for a lightweight gas turbine control strategy according to an exemplary embodiment. Figure 2 As shown, it should be noted that the lightweight gas turbine control strategy online verification system of the embodiment of the present disclosure is used to implement the control strategy optimization method of the gas turbine. Figure 2 As shown, the system may include a gas turbine control system, a gas turbine control system twin device, and a gas turbine control strategy verification and analysis device.

[0112] Among them, the gas turbine control system is used to automatically control the actual gas turbine (that is, the gas turbine entity proposed in some embodiments of the present disclosure), and is composed of an engineer station, an operator station, a history station, an OPC (OLE for Process Control, OLE for process control) station, a controller, an IO module and other devices. The controller includes a gas turbine control strategy configuration program, which is recorded as #1 gas turbine control strategy configuration program.

[0113] The gas turbine control system twin device is used to automatically control the gas turbine digital twin model (i.e., the twin model proposed in some embodiments of the present disclosure), and is composed of a controller (Y) and an edge computing device, wherein the controller (Y) includes a #2 gas turbine control strategy configuration program, and the edge computing device includes a gas turbine digital twin model;

[0114] The gas turbine control strategy verification and analysis device is used to deploy and automatically adjust the gas turbine digital twin model and analyze the function and performance of the gas turbine control strategy. It consists of a database module, a container module, and a microservice and application module.

[0115] The database module includes a time series database and a relational database. The time series database is used to store real-time data from the gas turbine control system and the twin device of the gas turbine control system; the relational database is used to store post-processing data for control strategy verification;

[0116] The container module includes a gas turbine model structure container, a gas turbine model parameterized data container, and a gas turbine model correction parameter data container;

[0117] The microservices and application modules include gas turbine model container encapsulation microservice, gas turbine edge computing device deployment microservice, gas turbine twin model automatic adjustment microservice, gas turbine digital twin model steady-state performance analysis microservice, gas turbine digital twin model dynamic performance analysis microservice, gas turbine digital twin model early warning microservice, gas turbine control strategy performance analysis microservice, and gas turbine control effect deviation early warning microservice.

[0118] In one embodiment, the gas turbine control system can transmit data to the gas turbine control strategy verification and analysis device through the OPC station. The twin device of the gas turbine control system receives operator control instructions, actual gas turbine unit sensor measurement signals, and container deployment files of the gas turbine control strategy verification and analysis device from the gas turbine control system through the real-time network of the gas turbine control system. The calculation data of the twin device of the gas turbine control system is transmitted to the gas turbine control strategy verification and analysis device through the OPC station.

[0119] As a possible example, the gas turbine control system can send a gas turbine control instruction, which will be sent to the gas turbine control system and the gas turbine control system twin device at the same time. The gas turbine control system including the #1 gas turbine control strategy configuration program controls the actual gas turbine and the gas turbine digital twin model in the edge computing device at the same time. At this time, closed-loop control is used for the actual gas turbine, and open-loop control is used for the digital twin model.

[0120] The key parameters of the gas turbine in the actual gas turbine unit and the digital twin model are sent to the gas turbine control strategy verification and analysis device through the OPC station and stored in the time series database; the key parameters include but are not limited to power, compressor outlet temperature, compressor outlet pressure, turbine outlet temperature, speed, etc.;

[0121] The gas turbine digital twin model steady-state performance analysis microservice will compare and analyze the key parameters of the gas turbine digital twin model in the gas turbine control system twin device with the actual operation data of the gas turbine and calculate the steady-state deviation;

[0122] The gas turbine digital twin model dynamic performance analysis microservice will compare and analyze the key parameters of the gas turbine digital twin model in the gas turbine control system twin device with the actual operation data of the gas turbine and calculate the dynamic deviation;

[0123] The gas turbine digital twin model early warning microservice will monitor and analyze the calculated steady-state deviation and dynamic deviation in real time, and store the monitoring and analysis results in the relational database. When the model deviation exceeds the set threshold, an early warning will be issued, indicating that the gas turbine characteristics represented by the digital twin model are different from the actual gas turbine;

[0124] At this time, the gas turbine digital twin model automatic adjustment microservice will be activated. This service will dynamically adjust the state variable correction parameters of the digital twin model according to the model deviation. The dynamic adjustment algorithm can use the optimal estimation algorithm such as the least squares method.

[0125] The correction parameters are updated to the gas turbine model correction parameter data container through the gas turbine fault-tolerant encapsulation microservice, and then distributed to the gas turbine control system twin device through the gas turbine edge computing device deployment microservice, thereby improving the steady-state and dynamic performance of the gas turbine digital twin model;

[0126] When the online adjustment method still cannot guarantee the model performance, the gas turbine model can be modified offline, including the model structure and modeling parameters, and then the modified model can be encapsulated into the gas turbine model structure container and the gas turbine model modeling parameter data container respectively, and deployed to the gas turbine control system twin device. When ensuring that the gas turbine digital twin model has a high degree of match with the actual gas turbine, the verification of the gas turbine control system twin device is completed.

[0127] In some embodiments of the present disclosure, after completing the verification of the twin device of the gas turbine control system, the verification of the gas turbine control strategy may be performed:

[0128] Adjust the control instructions of the gas turbine digital twin model in the edge computing device, that is, no longer receive the control instructions of the #1 gas turbine control strategy configuration program in controller 1, but receive the control instructions of the #2 gas turbine control strategy configuration program in controller (Y). At this time, controller 1 controls the actual gas turbine, and controller (Y) controls the gas turbine digital twin model in the edge computing device;

[0129] The key parameters of the gas turbine in the actual gas turbine unit and the digital twin model are sent to the gas turbine control strategy verification and analysis device through the OPC station and stored in the time series database;

[0130] The gas turbine control strategy analysis microservice will compare the control effect of controller 1 on the actual gas turbine with the control effect of controller (Y) on the gas turbine digital twin model in real time, and store the results of the comparative analysis in the relational database. The gas turbine control effect deviation warning microservice will monitor the control effect analysis results in real time. When the control deviation exceeds the threshold, an alarm will be issued and the control status data at this time will be stored in the relational database, which is convenient for offline analysis and optimization of the #2 gas turbine control strategy configuration program.

[0131] In some embodiments, online testing is performed to implement a gas turbine control strategy based on the actual operating conditions of the gas turbine. The gas turbine control system twin device can run an operating system in a real-time environment. The calculation step of the digital twin model should be less than 20ms, and it is directly connected to the real-time network of the gas turbine control system via Ethernet. The boundary conditions required by the gas turbine digital twin model, such as ambient temperature, ambient pressure, atmospheric humidity and other parameters, need to obtain the measurement signals of the actual gas turbine through the real-time network. The operator instructions of controller 1 and controller (Y) are all from the control signals of the actual operator station.

[0132] According to the lightweight gas turbine control strategy online verification system proposed in the embodiment of the present disclosure, only one controller and one edge computing device are used, and by regularly comparing and correcting the steady-state and dynamic accuracy of the gas turbine digital twin model and the actual gas turbine, the lightweight online verification of the gas turbine control strategy in a high-confidence test environment can be achieved. The verification of the gas turbine control strategy is based on the actual gas turbine production process, and the verification has high reliability and can be directly applied to the actual control of the gas turbine.

[0133] Figure 3 1 is a block diagram of a control strategy optimization device for a gas turbine according to an exemplary embodiment. Figure 3 The device includes a first execution unit 301, a first determination unit 302, a correction unit 303, a first execution unit 304, a second determination unit 305 and an adjustment unit 306.

[0134] The first execution unit 301 is used to respectively control the gas turbine entity and the twin model corresponding to the gas turbine entity to execute the target task by adopting the first control strategy, so as to obtain the first execution result of the gas turbine entity and the second execution result of the twin model;

[0135] A first determining unit 302 is used to determine a first operation deviation degree between the twin model and the gas turbine entity according to the first execution result and the second execution result;

[0136] The correction unit 303 is used to correct the model parameters of the twin model when the first operation deviation degree does not meet the preset conditions, and return to the step of using the first control strategy to respectively control the gas turbine entity and the twin model corresponding to the gas turbine entity to perform the target task;

[0137] The first execution unit 304 is used to control the gas turbine entity to perform the target task by adopting the first control strategy and to control the twin model to perform the target task by adopting the second control strategy when the first operation deviation degree meets the preset condition, so as to obtain a third execution result of the gas turbine entity and a fourth execution result of the twin model;

[0138] A second determination unit 305 is used to determine a second operation deviation degree between the twin model and the gas turbine entity according to the third execution result and the fourth execution result;

[0139] The adjustment unit 306 is used to adjust the second control strategy when the second operating deviation degree does not meet the preset conditions, and return to the steps of using the first control strategy to control the gas turbine entity to perform the target task, and using the second control strategy to control the twin model to perform the target task, until the second operating deviation degree meets the preset conditions, and the second control strategy is determined as the control strategy to complete the optimization.

[0140] In some embodiments of the present disclosure, the first execution result includes first operating data of the gas turbine entity in the process of executing the target task, and the second execution result includes second operating data of the twin model in the process of executing the target task. The first determination unit 302 can be specifically used to:

[0141] Calculating a first steady-state deviation value between the gas turbine entity and the twin model based on the first operating data and the second operating data;

[0142] Calculating a first dynamic deviation value between the gas turbine entity and the twin model based on the first operating data and the second operating data;

[0143] The device may further include:

[0144] The third determination unit is used to determine that the first operation deviation degree does not meet the preset condition when the first steady-state deviation value is greater than the first preset threshold and / or the first dynamic deviation value is greater than the second preset threshold.

[0145] In some embodiments of the present disclosure, the correction unit 303 may be specifically used to:

[0146] When the first running deviation degree does not meet the preset conditions, the extended Kalman filter algorithm is used to determine the model parameter correction value of the twin model;

[0147] The model parameters of the twin model are corrected according to the model parameter correction values.

[0148] In some embodiments of the present disclosure, the third execution result includes third operating data of the gas turbine entity in the process of executing the target task, and the fourth execution result includes fourth operating data of the twin model in the process of executing the target task. The second determination unit 305 can be specifically used to:

[0149] Calculating a second steady-state deviation value between the gas turbine entity and the twin model based on the third operating data and the fourth operating data;

[0150] Calculating a second dynamic deviation value between the gas turbine entity and the twin model based on the third operating data and the fourth operating data;

[0151] The device may also include:

[0152] The fourth determination unit is used to determine that the second operation deviation degree does not meet the preset condition when the second steady-state deviation value is greater than the third preset threshold and / or the second dynamic deviation value is greater than the fourth preset threshold.

[0153] In some embodiments of the present disclosure, the first execution unit 301 may be specifically used to:

[0154] Using a closed-loop control method, the gas turbine entity is controlled to perform a target task according to a first control strategy to obtain a first execution result;

[0155] An open-loop control method is adopted to control the twin model to execute the target task according to the first control strategy to obtain the second execution result.

[0156] In some embodiments of the present disclosure, the device may further include:

[0157] An acquisition unit, used for acquiring the operating environment information of the gas turbine entity in real time;

[0158] The updating unit is used to update the operating environment parameters of the twin model according to the operating environment information.

[0159] Regarding the device in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0160] According to the control strategy optimization device for a gas turbine proposed in the embodiment of the present disclosure, the deviation between the twin model and the gas turbine entity is reduced by continuously correcting the twin model according to the degree of operating deviation between the gas turbine entity and the twin model, thereby improving the realism of utilizing the twin model, and further improving the accuracy of verifying the control effect of the control strategy. In addition, by controlling the gas turbine entity and the corrected twin model to execute different control strategies, the operating effect deviation between the execution of different control strategies is obtained, and the second control strategy to be optimized is adjusted according to the degree of deviation, thereby improving the accuracy of optimizing the second control strategy.

[0161] Figure 4 4 is a block diagram of a device for a control strategy optimization method for a gas turbine according to an exemplary embodiment. For example, the device 400 may be an electronic device, such as a mobile phone, a computer, a digital broadcast terminal, a messaging device, a game console, a tablet device, a medical device, a fitness device, a personal digital assistant, etc.

[0162] Reference Figure 4 , the device 400 may include one or more of the following components: a processing component 402 , a memory 404 , a power component 406 , a multimedia component 408 , an audio component 410 , an input / output (I / O) interface 412 , a sensor component 414 , and a communication component 416 .

[0163] The processing component 402 generally controls the overall operation of the device 400, such as operations associated with display, phone calls, data communications, camera operations, and recording operations. The processing component 402 may include one or more processors 420 to execute instructions to complete all or part of the steps of the above-mentioned method. In addition, the processing component 402 may include one or more modules to facilitate the interaction between the processing component 402 and other components. For example, the processing component 402 may include a multimedia module to facilitate the interaction between the multimedia component 408 and the processing component 402.

[0164] The memory 404 is configured to store various types of data to support operations on the device 400. Examples of such data include instructions for any application or method operating on the device 400, contact data, phone book data, messages, pictures, videos, etc. The memory 404 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.

[0165] The power component 406 provides power to the various components of the device 400. The power component 406 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power for the device 400.

[0166] The multimedia component 408 includes a screen that provides an output interface between the device 400 and the user. In some embodiments, the screen may include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive input signals from the user. The touch panel includes one or more touch sensors to sense touch, slide, and gestures on the touch panel. The touch sensor may not only sense the boundaries of the touch or slide action, but also detect the duration and pressure associated with the touch or slide operation. In some embodiments, the multimedia component 408 includes a front camera and / or a rear camera. When the device 400 is in an operating mode, such as a shooting mode or a video mode, the front camera and / or the rear camera may receive external multimedia data. Each front camera and rear camera may be a fixed optical lens system or have a focal length and optical zoom capability.

[0167] The audio component 410 is configured to output and / or input audio signals. For example, the audio component 410 includes a microphone (MIC), and when the device 400 is in an operating mode, such as a call mode, a recording mode, and a speech recognition mode, the microphone is configured to receive an external audio signal. The received audio signal can be further stored in the memory 404 or sent via the communication component 416. In some embodiments, the audio component 410 also includes a speaker for outputting audio signals.

[0168] I / O interface 412 provides an interface between processing component 402 and peripheral interface modules, such as keyboards, click wheels, buttons, etc. These buttons may include but are not limited to: a home button, a volume button, a start button, and a lock button.

[0169] The sensor assembly 414 includes one or more sensors for providing various aspects of status assessment for the device 400. For example, the sensor assembly 414 can detect the open / closed state of the device 400, the relative positioning of components, such as the display and keypad of the device 400, and the sensor assembly 414 can also detect the position change of the device 400 or a component of the device 400, the presence or absence of user contact with the device 400, the orientation or acceleration / deceleration of the device 400, and the temperature change of the device 400. The sensor assembly 414 may include a proximity sensor configured to detect the presence of nearby objects without any physical contact. The sensor assembly 414 may also include an optical sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, the sensor assembly 414 may also include an accelerometer, a gyroscope sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.

[0170] The communication component 416 is configured to facilitate wired or wireless communication between the device 400 and other devices. The device 400 can access a wireless network based on a communication standard, such as WiFi, 2G or 3G, or a combination thereof. In an exemplary embodiment, the communication component 416 receives a broadcast signal or broadcast-related information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communication component 416 also includes a near field communication (NFC) module to facilitate short-range communication. For example, the NFC module can be implemented based on radio frequency identification (RFID) technology, infrared data association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology and other technologies.

[0171] In an exemplary embodiment, the apparatus 400 may be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to perform the above method.

[0172] In an exemplary embodiment, a non-transitory computer-readable storage medium including instructions is also provided, such as a memory 404 including instructions, and the instructions can be executed by a processor 420 of the device 400 to perform the above method. For example, the non-transitory computer-readable storage medium can be a ROM, a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, etc.

[0173] In an exemplary embodiment, a computer program product is also provided, comprising a computer program, which implements the above method when executed by the processor 420 of the device 400 .

[0174] Those skilled in the art will readily appreciate other embodiments of the present invention after considering the specification and practicing the invention disclosed herein. The present disclosure is intended to cover any variations, uses or adaptations of the present invention that follow the general principles of the present invention and include common knowledge or customary techniques in the art that are not disclosed in the present disclosure. The description and examples are to be considered exemplary only, and the true scope and spirit of the present invention are indicated by the following claims.

[0175] It should be understood that the present invention is not limited to the exact construction that has been described above and shown in the drawings and that various modifications and changes may be made without departing from the scope thereof. The scope of the present invention is limited only by the appended claims.

Claims

1. A control strategy optimization method for a gas turbine, characterized in that: include: Using a first control strategy to respectively control a gas turbine entity and a twin model corresponding to the gas turbine entity to execute a target task, and obtaining a first execution result of the gas turbine entity and a second execution result of the twin model; Determining a first operating deviation degree between the twin model and the gas turbine entity according to the first execution result and the second execution result; In the case where the first operation deviation degree does not meet the preset conditions, the model parameters of the twin model are corrected, and the step of using the first control strategy to respectively control the gas turbine entity and the twin model corresponding to the gas turbine entity to perform the target task is returned to execution; When the first operation deviation degree meets the preset condition, the first control strategy is adopted to control the gas turbine entity to perform the target task, and the second control strategy is adopted to control the twin model to perform the target task, so as to obtain a third execution result of the gas turbine entity and a fourth execution result of the twin model; Determining a second operation deviation degree between the twin model and the gas turbine entity according to the third execution result and the fourth execution result; When the second operating deviation degree does not meet the preset conditions, adjust the second control strategy and return to the step of using the first control strategy to control the gas turbine entity to perform the target task and using the second control strategy to control the twin model to perform the target task until the second operating deviation degree meets the preset conditions and the second control strategy is determined as the optimized control strategy.

2. The control strategy optimization method for a gas turbine according to claim 1, characterized in that: The first execution result includes first operating data of the gas turbine entity in the process of executing the target task, and the second execution result includes second operating data of the twin model in the process of executing the target task; The determining, according to the first execution result and the second execution result, a first operation deviation degree between the twin model and the gas turbine entity comprises: Calculating a first steady-state deviation value between the gas turbine entity and the twin model according to the first operating data and the second operating data; Calculating a first dynamic deviation value between a gas turbine entity and a twin model according to the first operating data and the second operating data; After determining the first operation deviation degree between the twin model and the gas turbine entity according to the first execution result and the second execution result, the method further includes: When the first steady-state deviation value is greater than a first preset threshold value and / or the first dynamic deviation value is greater than a second preset threshold value, it is determined that the first operation deviation degree does not meet a preset condition.

3. The control strategy optimization method for a gas turbine according to claim 1, characterized in that: When the first operation deviation degree does not meet a preset condition, correcting the model parameters of the twin model includes: When the first operation deviation degree does not meet the preset condition, an extended Kalman filter algorithm is used to determine the model parameter correction value of the twin model; The model parameters of the twin model are corrected according to the model parameter correction values.

4. The control strategy optimization method for a gas turbine according to claim 1, characterized in that: The third execution result includes third operating data of the gas turbine entity in the process of executing the target task, and the fourth execution result includes fourth operating data of the twin model in the process of executing the target task; Determining a second operation deviation degree between the twin model and the gas turbine entity according to the third execution result and the fourth execution result includes: Calculating a second steady-state deviation value between the gas turbine entity and the twin model according to the third operating data and the fourth operating data; Calculating a second dynamic deviation value between the gas turbine entity and the twin model according to the third operating data and the fourth operating data; After determining the second operation deviation degree between the twin model and the gas turbine entity according to the third execution result and the fourth execution result, the method further includes: When the second steady-state deviation value is greater than a third preset threshold and / or the second dynamic deviation value is greater than a fourth preset threshold, it is determined that the second operation deviation degree does not meet a preset condition.

5. The control strategy optimization method for a gas turbine according to claim 1, characterized in that: The adopting of the first control strategy to respectively control the gas turbine entity and the twin model corresponding to the gas turbine entity to perform the target task, and obtaining a first execution result of the gas turbine entity and a second execution result of the twin model, includes: Using a closed-loop control method, according to the first control strategy, the gas turbine entity is controlled to perform the target task, and the first execution result is obtained; An open-loop control method is adopted to control the twin model to execute the target task according to the first control strategy to obtain the second execution result.

6. The control strategy optimization method for a gas turbine according to claim 1, characterized in that: The method further comprises: Acquiring operating environment information of the gas turbine entity in real time; Update the operating environment parameters of the twin model according to the operating environment information.

7. A control strategy optimization device for a gas turbine, characterized in that: include: A first execution unit, configured to respectively control the gas turbine entity and the twin model corresponding to the gas turbine entity to execute a target task by adopting a first control strategy, and obtain a first execution result of the gas turbine entity and a second execution result of the twin model; A first determining unit, configured to determine a first operating deviation degree between the twin model and the gas turbine entity according to the first execution result and the second execution result; A correction unit, configured to correct the model parameters of the twin model when the first operation deviation degree does not meet the preset conditions, and return to the step of using the first control strategy to respectively control the gas turbine entity and the twin model corresponding to the gas turbine entity to perform the target task; A first execution unit is used to control the gas turbine entity to perform the target task by adopting the first control strategy, and to control the twin model to perform the target task by adopting the second control strategy, when the first operation deviation degree meets a preset condition, to obtain a third execution result of the gas turbine entity and a fourth execution result of the twin model; A second determining unit, configured to determine a second operation deviation degree between the twin model and the gas turbine entity according to the third execution result and the fourth execution result; An adjustment unit is used to adjust the second control strategy when the second operating deviation degree does not meet the preset conditions, return to the steps of using the first control strategy to control the gas turbine entity to perform the target task, and use the second control strategy to control the twin model to perform the target task, until the second operating deviation degree meets the preset conditions, and determine the second control strategy as the control strategy to complete the optimization.

8. An electronic device, characterized in that: include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the method according to any one of claims 1 to 6 is implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.

10. A computer program product, comprising a computer program, characterized in that The computer program implements the method according to any one of claims 1 to 6 when executed by a processor.

Images