Methods, devices, electronic equipment and storage media for flashback control of hydrogen-mixed gas turbines

Abstract

This invention provides a method, apparatus, electronic device, and storage medium for controlling backfire in a hydrogen-blended gas turbine. The method first calculates a backfire database for the combustion chamber based on a three-dimensional flow net model of the combustion chamber. Then, using this backfire database and an intelligent algorithm, a proxy data model of the combustion chamber is established to construct combustion state characterization parameters. Backfire characterization parameters are then constructed using the proxy data model. Finally, backfire control is performed based on these backfire characterization parameters. This invention effectively prevents backfire in hydrogen-blended gas turbines by adjusting control parameters such as fuel quantity and hydrogen blending ratio, based on actual monitoring of the backfire state, backfire margin, and backfire judgment index during operation.

Description

Technical Field

[0001] This invention relates to the field of hydrogen-mixed gas turbine technology, and in particular to a method, apparatus, electronic device, and storage medium for controlling the backfire of a hydrogen-mixed gas turbine. Background Technology

[0002] When hydrogen fuel is used as a clean fuel in gas turbines, it can achieve zero carbon emissions. However, in hydrogen-rich fuels, the introduction of hydrogen significantly increases both the laminar and turbulent flame velocities, while the axial velocity decreases markedly under strong swirling conditions. This significantly increases the risk of backfire in the center flow of the gas turbine combustor. Currently, most methods to reduce gas turbine backfire involve modifying the combustor structure; however, due to the variable operating conditions of gas turbines, backfire can still occur in the combustor.

[0003] CN104534474A discloses a gas turbine and a method for detecting backfire using the gas turbine. The gas turbine includes a central cone, a casing, and multiple swirl blades. The central cone is located within the casing, and a premixing channel is formed between the central cone and the casing. The swirl blades are arranged circumferentially on the inner wall of the casing. Temperature sensors are installed on the central cone and within the premixing channel. The placement of temperature sensors near the tip of the central cone and near the outlet of the premixing channel allows for the detection of core region backfire and boundary layer backfire in the fuel nozzle, respectively. This fully considers the main mechanisms leading to backfire in the combustion chamber nozzle and provides a guarantee for the safe operation of the fuel nozzle.

[0004] CN203671654U discloses a combustion chamber for a gas turbine. The head structure of this combustion chamber includes a main combustion stage and a pre-combustion stage. In the head structure, a pre-combustion stage wall, an inner wall of the main combustion stage, and an outer wall of the main combustion stage are coaxially arranged from the inside out. A main combustion stage mixing zone is formed between the inner and outer walls of the main combustion stage. The inner wall of the main combustion stage expands outward at a certain angle to the axis of the combustion chamber, causing the flow channel of the main combustion stage mixing zone to gradually narrow along the outlet direction. Furthermore, a pre-combustion stage baffle protrudes radially outward at the outlet end of the pre-combustion stage wall, and an isolation groove is formed between the outlet end of the inner wall of the main combustion stage and the pre-combustion stage baffle. This combustion chamber with the above structure effectively suppresses backfire with a simple structure.

[0005] However, the aforementioned methods and devices are ineffective for active backfire control in hydrogen-mixed gas turbines. Furthermore, they do not address backfire monitoring and active control within the gas turbine control system. Summary of the Invention

[0006] In view of the problems existing in the prior art, the present invention provides a method, device, electronic equipment and storage medium for controlling the backfire of a hydrogen-mixed gas turbine. By calculating data from a three-dimensional flow net model of the combustion chamber and real-time operating data of the hydrogen-mixed gas turbine, backfire characteristic parameters of the hydrogen-mixed gas turbine are constructed, realizing predictive control and active control of backfire in the hydrogen-mixed gas turbine, and ensuring the safe and stable operation of the hydrogen-mixed gas turbine.

[0007] To achieve this objective, the present invention adopts the following technical solution:

[0008] In a first aspect, the present invention provides a method for controlling the flashback of a hydrogen-mixed gas turbine, comprising:

[0009] S1: Based on the three-dimensional flow net model of the combustion chamber, the combustion chamber flashback database of the hydrogen-mixed gas turbine is calculated;

[0010] S2: Using the aforementioned combustion chamber tempering database and employing intelligent algorithms, establish a combustion chamber proxy data model and construct combustion state characterization parameters for the combustion chamber;

[0011] S3: Construct tempering characterization parameters using the combustion chamber proxy data model;

[0012] S4: Perform tempering control according to the tempering characterization parameters.

[0013] The hydrogen-mixed gas turbine backfire control method of this invention calculates a backfire database of the hydrogen-mixed gas turbine based on a three-dimensional flow net model of the combustion chamber. Using the combustion chamber backfire database, combustion state characterization parameters and backfire characterization parameters of the combustion chamber are constructed. Based on these backfire characterization parameters, predictive and active control of backfire in the hydrogen-mixed gas turbine is performed to reduce the backfire that may occur during the operation of the hydrogen-mixed gas turbine, ensuring the safe and stable operation of the hydrogen-mixed gas turbine, and has the prospect of large-scale application.

[0014] Preferably, in step S1, a three-dimensional flow net model of the combustion chamber is used to calculate the flame velocity, reactant inflow velocity, turbulence intensity, and flashback state of the hydrogen-blended gas turbine under different compressor outlet temperatures, different compressor outlet pressures, different combustion chamber inlet air flow rates, different hydrogen blending ratios, different total fuel quantities, different fuel pipeline distribution ratios, different fuel temperatures, and different fuel pressures, thereby constructing a combustion chamber flashback database.

[0015] Preferably, the calculation of the combustion chamber flashback database for the hydrogen-blended gas turbine based on the three-dimensional flow net model of the combustion chamber in step S1 includes:

[0016] S101, Set the boundary conditions for the calculation of the three-dimensional flow net model of the combustion chamber;

[0017] The boundary conditions calculated by the three-dimensional flow net model of the combustion chamber include compressor outlet temperature, compressor outlet pressure, combustion chamber inlet air flow rate, hydrogen blending ratio, total fuel volume, fuel pipeline distribution ratio, fuel temperature, and fuel pressure.

[0018] S102, run the three-dimensional flow net model of the combustion chamber, obtain the model calculation results, and record the flame velocity, reactant inflow velocity, turbulence intensity, and tempering state;

[0019] S103, through the database storage command, stores the compressor outlet temperature, compressor outlet pressure, combustion chamber inlet air flow rate, hydrogen blending ratio, total fuel, fuel pipeline distribution ratio, fuel temperature, fuel pressure, flame velocity, reactant inflow velocity, turbulence intensity, and tempering state into the combustion chamber tempering database;

[0020] S104, modify the boundary conditions of different three-dimensional flow net models of the combustion chamber, and repeat the above steps.

[0021] Preferably, the intelligent algorithm described in step S2 includes machine learning or deep learning.

[0022] Preferably, the combustion chamber condition characterization parameters are represented by the following function:

[0023] S L =f1(T2,P2,G2,H r G f D r ,T f ,P f )

[0024] u r =f2(T2,P2,G2,H r G f D r ,T f ,P f )

[0025] T u =f3(T2,P2,G2,H) r G f D r ,T f ,P f )

[0026] H s =f4(T2,P2,G2,H r G f D r ,T f ,P f )

[0027] Where T2 is the compressor outlet temperature, P2 is the compressor outlet pressure, G2 is the combustion chamber inlet air flow rate, and H... r For the hydrogen doping ratio, G f For the total fuel quantity, D r For the fuel flow ratio of each nozzle, T f For fuel temperature, P f For fuel quantity pressure, S L For laminar flame velocity, u r T is the inflow velocity of the reactants. u H represents the turbulence intensity. s It is in the tempered state.

[0028] Preferably, functions f1, f2, and f3 are obtained using a support vector machine regression algorithm, and function f4 is obtained using a support vector machine classification algorithm.

[0029] Preferably, the tempering characterization parameters in step S3 include tempering margin ξ and tempering judgment index λ.

[0030] Preferably, the tempering margin ξ is calculated according to the following formula:

[0031]

[0032] Where ξ is the tempering margin, S L For laminar flame velocity, T u For turbulence intensity, u r The reactant inflow velocity.

[0033] Preferably, the tempering judgment index λ is calculated according to the following formula:

[0034]

[0035] Preferably, step S4, which involves tempering control based on the tempering characterization parameters, includes:

[0036] A flashback control loop is constructed based on the flashback margin ξ. By limiting the amount of fuel, the flashback margin is prevented from shrinking further, thereby achieving flashback control.

[0037] A hydrogen doping ratio limiting loop is constructed based on the tempering margin ξ, and tempering control is achieved by limiting the hydrogen doping ratio.

[0038] A flashback protection circuit is constructed based on the flashback state, flashback margin ξ, and flashback judgment index λ to perform flashback alarm and trip protection.

[0039] Preferably, the step of constructing a flashback protection circuit based on flashback state, flashback occurrence margin ξ, and flashback judgment index λ to perform flashback alarm and trip protection includes the following steps:

[0040] When the flashback detection index λ exceeds the flashback detection index threshold, a flashback trip signal is issued.

[0041] When the tempering margin ξ exceeds the tempering margin trip value, a tempering trip signal is issued.

[0042] When a flashback occurs, a flashback trip signal is issued.

[0043] Secondly, the present invention also provides a hydrogen-mixed gas turbine flashback control device, comprising:

[0044] The first generation module is used to generate a combustion chamber tempering database based on the three-dimensional flow net data of the combustion chamber.

[0045] The second generation module is used to generate a calculation model for combustion state characterization parameters of the combustion chamber based on the combustion chamber tempering database;

[0046] The third generation module is used to generate combustion chamber flashback characterization parameters based on combustion chamber combustion state characterization parameters;

[0047] The control module is used to perform backfire control on the hydrogen-mixed gas turbine based on the combustion state characterization parameters of the combustion chamber and the standard parameters of the combustion chamber backfire.

[0048] In this invention, the first generation module, the second generation module, the third generation module, and the control module are connected in sequence, and the data of each generation module is transmitted in sequence. Finally, the control module performs backfire control on the hydrogen-gas turbine.

[0049] Thirdly, the present invention also provides an electronic device, including a memory and a processor, wherein the processor runs a program corresponding to the executable program code by reading executable program code stored in the memory, for implementing the hydrogen-mixed gas turbine backfire control method described in the first aspect.

[0050] Fourthly, the present invention also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the hydrogen-mixed gas turbine flashover control method described in the first aspect.

[0051] Fifthly, the present invention also provides a computer program product, including a computer program that, when executed by a processor, implements the hydrogen-mixed gas turbine flashover control method described in the first aspect.

[0052] Compared with the prior art, the present invention has at least the following beneficial effects:

[0053] The hydrogen-mixed gas turbine backfire control method provided by this invention monitors and actively controls backfire in the hydrogen-mixed gas turbine from the perspective of the gas turbine control system. By calculating data from the three-dimensional flow net model of the combustion chamber and the real-time operating data of the hydrogen-mixed gas turbine, backfire characteristic parameters of the hydrogen-mixed gas turbine are constructed, realizing predictive and active control of backfire in the hydrogen-mixed gas turbine, and ensuring the safe and stable operation of the hydrogen-mixed gas turbine. Attached Figure Description

[0054] Figure 1 This is a schematic diagram of the hydrogen-mixed gas turbine flashback control system provided by the present invention.

[0055] Figure 2 This is a flowchart of a hydrogen-mixed gas turbine backfire control method according to an embodiment of the present invention.

[0056] Figure 3 This is a flowchart of step S1 of an embodiment of the present invention, in which the combustion chamber backfire database of a hydrogen-mixed gas turbine is calculated based on the three-dimensional flow net model of the combustion chamber.

[0057] Figure 4 In one embodiment of the present invention, step S2 utilizes the combustion chamber backfire database and employs an intelligent algorithm to establish a combustion chamber proxy data model and construct a flowchart of combustion chamber combustion state characterization parameters.

[0058] Figure 5 This is a flowchart illustrating tempering control using tempering margin in one embodiment of the present invention.

[0059] Figure 6 This is a structural diagram of the hydrogen-gas turbine reheat control loop according to an embodiment of the present invention.

[0060] Figure 7 This is a minimum value selection control diagram, taken as an example of the GE 9F gas turbine control loop in one embodiment of the present invention.

[0061] Figure 8 This is a flowchart illustrating the control of hydrogen doping ratio limits using tempering margin, according to an embodiment of the present invention.

[0062] Figure 9 This is a structural diagram of a hydrogen blending gas turbine hydrogen blending ratio limiting loop according to an embodiment of the present invention.

[0063] Figure 10 This is a flowchart of a method for tempering protection using tempering characterization parameters, according to an embodiment of the present invention.

[0064] Figure 11 This is a schematic diagram of the backfire protection logic of a hydrogen-mixed gas turbine according to an embodiment of the present invention.

[0065] Figure 12This is a structural diagram of a hydrogen-mixed gas turbine flashover control device according to an embodiment of the present invention.

[0066] Figure 13 This is a block diagram of an electronic device for a hydrogen-gas turbine backfire control method according to an embodiment of the present invention. Detailed Implementation

[0067] The technical solution of the present invention will be further described below with reference to the accompanying drawings and specific embodiments.

[0068] The present invention will now be described in further detail. However, the examples described below are merely simplified examples of the present invention and do not represent or limit the scope of protection of the present invention. The scope of protection of the present invention is determined by the claims.

[0069] This invention provides a hydrogen-mixed gas turbine flashback control system, the schematic diagram of which is shown below. Figure 1 As shown, the tempering control system includes:

[0070] Gas turbine control system 1. Component model server 2. Combustion chamber tempering database server 3. Combustion chamber tempering proxy model training server 4. Combustion chamber tempering proxy model edge computing device 5. Combustion chamber tempering controller 6.

[0071] The system comprises: a gas turbine control system 1, which is the control equipment for the hydrogen-blended gas turbine; a component model server 2, which stores the component design parameters and three-dimensional flow network model of the hydrogen-blended gas turbine; a combustion chamber tempering database server 3, which stores the combustion chamber tempering data calculated by the component model server 2, including compressor outlet temperature, compressor outlet pressure, combustion chamber inlet air flow rate, hydrogen blending ratio, total fuel volume, fuel pipeline distribution ratio, fuel temperature, fuel pressure, flame velocity, reactant inflow velocity, turbulence intensity, tempering boundary, and tempering state; a combustion chamber tempering proxy model training server 4, which includes a combustion chamber tempering proxy model and a combustion chamber tempering proxy model training calculation program; a combustion chamber tempering proxy model edge computing device 5, which includes a memory, processor, real-time operating system, and a combustion chamber tempering characteristic parameter calculation program; and a combustion chamber tempering controller 6, which includes tempering control strategy, hydrogen blending ratio limitation strategy, and tempering protection strategy.

[0072] The component model server 2 calculates the combustion chamber three-dimensional flow net model, obtains combustion chamber tempering calculation data, and stores it in the combustion chamber tempering database server 3 via communication.

[0073] The data in the combustion chamber tempering database server 3 is transmitted to the combustion chamber tempering proxy model training server 4 via communication.

[0074] The combustion chamber tempering proxy model training server 4 uses the combustion chamber tempering database and employs intelligent algorithms such as machine learning and deep learning to establish a combustion chamber proxy data model, and then downloads the combustion chamber proxy mathematical model to the combustion chamber tempering proxy model edge computing device 5 via communication.

[0075] The edge computing device 5 for the combustion chamber backfire proxy model is used to calculate the combustion chamber backfire characteristic parameters, including the backfire judgment index and backfire occurrence margin, using the actual sensor data of the gas turbine and the combustion chamber proxy data model. Then, it is transmitted to the combustion chamber backfire controller 6 through the real-time network of the gas turbine control system 1.

[0076] The combustion chamber flashback controller 6 is used to calculate control commands based on flashback characteristic parameters, using flashback control loop, hydrogen doping ratio limiting loop, and flashback protection loop. Then, it is transmitted to controller A and controller B of the gas turbine control system 1 through the real-time network of the gas turbine control system 1.

[0077] As an embodiment of the present invention, a method for controlling the flashback of a hydrogen-mixed gas turbine is provided, the flowchart of which is shown below. Figure 2 As shown, it includes:

[0078] S1: Using a three-dimensional flow net model of the combustion chamber, the flame velocity, reactant inflow velocity, turbulence intensity, and flashback state of the hydrogen-blended gas turbine under different compressor outlet temperatures, different compressor outlet pressures, different combustion chamber inlet air flow rates, different hydrogen blending ratios, different total fuel amounts, different fuel pipeline distribution ratios, different fuel temperatures, and different fuel pressures are calculated to construct a combustion chamber flashback database.

[0079] S2: Using the aforementioned combustion chamber tempering database and employing intelligent algorithms, establish a combustion chamber proxy data model and construct combustion state characterization parameters for the combustion chamber;

[0080] The intelligent algorithm includes machine learning or deep learning;

[0081] Preferably, the combustion chamber condition characterization parameters are represented by the following function:

[0082] S L =f1(T2,P2,G2,H r G f D r ,T f ,P f )

[0083] u r =f2(T2,P2,G2,H r G f D r ,T f ,Pf )

[0084] T u =f3(T2,P2,G2,H) r G f D r ,T f ,P f )

[0085] H s =f4(T2,P2,G2,H r G f D r ,T f ,P f )

[0086] Where T2 is the compressor outlet temperature, P2 is the compressor outlet pressure, G2 is the combustion chamber inlet air flow rate, and H... r For the hydrogen doping ratio, G f For the total fuel quantity, D r For the fuel flow ratio of each nozzle, T f For fuel temperature, P f For fuel quantity pressure, S L For laminar flame velocity, u r T is the inflow velocity of the reactants. u H represents the turbulence intensity. s It is in the tempered state;

[0087] S3: Construct tempering characterization parameters using the combustion chamber proxy data model;

[0088] Hydrogen-gas turbines are prone to backfire, mainly because hydrogen fuel has a short combustion delay and a fast flame propagation speed. When the flame speed exceeds the reactant speed, backfire is likely to occur.

[0089] In some instances, the tempering margin ξ and tempering judgment index λ are constructed based on laminar flame velocity, reactant inflow velocity, and turbulence intensity.

[0090] The tempering margin ξ is calculated using the following formula:

[0091]

[0092] Where ξ is the tempering margin, S L For laminar flame velocity, T u For turbulence intensity, u r The reactant inflow velocity.

[0093] Optionally, in the embodiments of this application, ξ is used to measure the margin for backfire. Under normal circumstances, ξ should be within a reasonable range, which can be 0.2 to 0.6. The smaller ξ is, the smaller the safety margin for backfire. However, a larger safety margin is not necessarily better. A larger ξ can easily cause the combustion chamber to shut down.

[0094] The tempering criterion λ is calculated using the following formula:

[0095]

[0096] When λ is greater than 1, it indicates that the flame propagation speed is greater than the reactant flow speed, and the hydrogen-gas turbine has experienced backfire; when λ is less than or equal to 1, it indicates that the flame propagation speed is not greater than the reactant flow speed, and the hydrogen-gas turbine has not yet experienced backfire.

[0097] S4: Perform tempering control based on the tempering characterization parameters;

[0098] A flashback control loop is constructed based on the flashback margin ξ. By limiting the amount of fuel, the flashback margin is prevented from shrinking further, thereby achieving flashback control.

[0099] A hydrogen doping ratio limiting loop is constructed based on the tempering margin ξ, and tempering control is achieved by limiting the hydrogen doping ratio.

[0100] A flashback protection circuit is constructed based on the flashback state, flashback margin ξ, and flashback judgment index λ to perform flashback alarm and trip protection.

[0101] This invention can monitor the flashback state, flashback margin ξ, and flashback judgment index λ during the operation of a hydrogen-blended gas turbine. By adjusting control parameters such as fuel quantity and hydrogen blending ratio, flashback in the hydrogen-blended gas turbine can be prevented.

[0102] As an embodiment of the present invention, the flowchart for calculating the combustion chamber flashback database of the hydrogen-mixed gas turbine based on the three-dimensional flow net model of the combustion chamber in step S1 is as follows: Figure 3 As shown, it includes:

[0103] S101, Set the boundary conditions for the calculation of the three-dimensional flow net model of the combustion chamber;

[0104] The boundary conditions calculated by the three-dimensional flow net model of the combustion chamber include compressor outlet temperature, compressor outlet pressure, combustion chamber inlet air flow rate, hydrogen blending ratio, total fuel volume, fuel pipeline distribution ratio, fuel temperature, and fuel pressure.

[0105] S102, run the three-dimensional flow net model of the combustion chamber, obtain the model calculation results, and record the flame velocity, reactant inflow velocity, turbulence intensity, and tempering state;

[0106] S103, through the database storage command, stores the compressor outlet temperature, compressor outlet pressure, combustion chamber inlet air flow rate, hydrogen blending ratio, total fuel, fuel pipeline distribution ratio, fuel temperature, fuel pressure, flame velocity, reactant inflow velocity, turbulence intensity, and tempering state into the combustion chamber tempering database;

[0107] S104, modify the boundary conditions of different three-dimensional flow net models of the combustion chamber, and repeat the above steps.

[0108] This embodiment employs a single-variable control method, changing one parameter at a time. In some embodiments, when changing the hydrogen blending ratio parameter, other parameters are kept constant, and the hydrogen blending ratio is varied in 1% increments within the range of 0-100%. In other embodiments, when changing the total fuel quantity parameter, other parameters are kept constant, and the total fuel quantity is varied in 1% increments within the range of ignition fuel quantity to full-load fuel quantity. This process is repeated to construct a combustion chamber backfire database that satisfies any combination of parameters under all operating conditions.

[0109] In one embodiment of the present invention, step S2 utilizes the combustion chamber tempering database and employs an intelligent algorithm to establish a combustion chamber proxy data model, and constructs a flowchart of combustion chamber combustion state characterization parameters as follows: Figure 4 As shown, it includes the following steps:

[0110] S201 uses intelligent algorithms such as machine learning and deep learning to construct calculation models for combustion state characterization parameters in the combustion chamber, such as flame velocity, reactant flow velocity, and turbulence intensity.

[0111] In some embodiments, functions f1, f2, and f3 are obtained using a support vector machine regression algorithm. Because the combustion chamber data model has highly nonlinear characteristics, a kernel function approach is used to first map each independent variable to a high-dimensional space, ensuring that the mapped variables in the high-dimensional space have a certain degree of linearity, before utilizing the support vector machine algorithm.

[0112] Taking flame velocity characterization parameters as an example, the construction process is explained. The flame velocity characterization parameters are constructed using a support vector machine algorithm to create the function f1.

[0113] S L =f1(x)=w T *φ(x)+b

[0114] Where, k(x) i ,x j )=φ(x i ) T *φ(x j )

[0115] Choose the Gaussian kernel function, i.e.

[0116]

[0117] Where σ is the adjustable hyperparameter of the Gaussian kernel.

[0118] The objective function of this algorithm is:

[0119]

[0120] And it satisfies the following constraints:

[0121] |S L -(w T *φ(x i )+b)|≤ε

[0122] Where ε is a slack variable.

[0123] In some embodiments, the function f4 is obtained using a support vector machine classification algorithm, where no refractory event is marked as 1 and refractory event is marked as 0.

[0124] S202 utilizes the combustion chamber flashback database and employs an optimization algorithm to train the calculation model for combustion state characterization parameters of the combustion chamber.

[0125] After constructing the flame velocity calculation model, 70% of the data from the combustion chamber flashback database was randomly selected to train the combustion chamber surrogate data model, and then the remaining 30% of the data was used for validation. During the training process, the objective function was minimized while the independent variables satisfied a certain scope.

[0126] In some embodiments, stochastic gradient optimization algorithms may be used to optimize and solve the model.

[0127] S203. Evaluate the verification accuracy of the combustion chamber combustion state characterization parameter calculation model. If the accuracy meets the requirements, training ends. If the accuracy is insufficient, modify the model hyperparameters and repeat the above steps. If the accuracy is still insufficient after modifying the model hyperparameters, modify the modeling method and repeat the above process.

[0128] In some embodiments, the verification accuracy of the calculation models for flame velocity, reactant inflow velocity, and turbulence intensity is evaluated using the following formula:

[0129]

[0130] in, The relative average deviation between the accuracy of the flame velocity model calculation and the calculation data of the three-dimensional flow net model of the combustion chamber is represented by m, which represents the number of samples in the combustion chamber tempering database. i This indicates the flame velocity calculated by the three-dimensional flow net model of the combustion chamber, and ε1 indicates the threshold for successful verification, which can be taken as 2%.

[0131] In other embodiments, the verification accuracy of the tempering state calculation model is evaluated using the following formula:

[0132]

[0133] Where, ∑ 所有正样本 rank represents the sum of the sorted index values ​​of all positive samples, M and N are the number of positive and negative samples respectively, and ε2 represents the threshold for successful validation, which can be 98%.

[0134] As an embodiment of the present invention, a flowchart of tempering control using tempering occurrence margin is shown below. Figure 5 As shown, it includes:

[0135] S301 calculates the tempering margin using real-time running data;

[0136] The real-time input data required for calculating the tempering margin is obtained from the gas turbine control system, and the tempering margin is calculated in real time according to the tempering margin calculation model.

[0137] S302, using the tempering margin, constructs a tempering control loop and calculates the fuel quantity command for the tempering control loop;

[0138] By utilizing the tempering margin, a tempering control loop is constructed, and tempering control is achieved by controlling the amount of fuel.

[0139] In some embodiments, the backfire margin is obtained through a backfire margin calculation module, and the deviation from the backfire margin limit is input to a PID controller. The controller's output is superimposed on the current actual fuel quantity to obtain a backfire control fuel quantity command. This control loop can control backfire by limiting the fuel quantity. For example, some gas turbines, after hydrogen blending, can only operate in a low-load region. If the load is increased further after a fixed hydrogen blending ratio, backfire is likely to occur. Under the action of this control algorithm, if the backfire margin continuously decreases during the gas turbine load increase process, when the backfire margin limit is reached, the backfire control fuel quantity will be selected. At this time, the gas turbine will stop increasing the load to avoid backfire. The backfire control loop structure diagram is shown below. Figure 6 As shown. The tempering margin limit value can be selected based on the safety margin, with the threshold ξ0 being chosen.

[0140] S303 uses the fuel quantity command of the backfire control loop to control the fuel quantity.

[0141] The amount of fuel in the flashback control loop needs to be included in the overall fuel quantity control of the hydrogen-gas turbine.

[0142] In some embodiments, a gas turbine typically has multiple control loops, such as a start-up control loop, a speed control loop, an acceleration control loop, and a temperature control loop. These multiple control loops are selected by a minimum value selection module, and then compared with the minimum fuel quantity using a maximum value selection to calculate the total fuel quantity command. To achieve backfire control, a backfire control loop is added to the minimum value selection module, limiting backfire occurrence through fuel quantity control. Taking the GE 9F gas turbine control loop as an example, the minimum value selection control is as follows: Figure 7 As shown.

[0143] A flowchart of a method for limiting the hydrogen doping ratio using tempering margin in one embodiment of the present invention is shown below. Figure 8 As shown, it includes the following steps:

[0144] S401 uses real-time operating data to calculate the hydrogen doping ratio limit under the current operating conditions;

[0145] Based on the current T2, P2, G2, H r G f D r ,T f ,P f Actual value, calculated to obtain S L u r T u H s And calculate ξ. Use the bisection method to continuously adjust H. r The proportion is calculated until the maximum H is found that satisfies ξ less than the threshold. r 0, and H s Maximum H when tempering does not occur r 1. Then select H r 0 and H r The minimum value of 1 is used as the output value of the hydrogen doping ratio limit calculation module.

[0146] S402, using the hydrogen blending ratio limit value, constructs a hydrogen blending ratio limit control loop, and calculates the hydrogen blending ratio control command, hydrogen fuel quantity control command, and natural gas fuel quantity control command;

[0147] The maximum hydrogen blending ratio that will not cause backfire under the current input boundary is obtained through the hydrogen blending ratio limit calculation module. Then, after passing through the minimum value selection module with the hydrogen blending ratio setpoint, the hydrogen blending ratio control command is obtained. Based on the total fuel quantity command and the hydrogen blending ratio control command, the hydrogen fuel quantity control command and the natural gas fuel quantity control command can be obtained. Under this control algorithm, if the gas turbine needs to increase the hydrogen blending ratio, the control system will limit the gas turbine to operate within a safe hydrogen blending ratio range. The hydrogen blending ratio limit loop structure diagram is shown below. Figure 9 As shown.

[0148] A flowchart of a tempering protection method using tempering characterization parameters according to an embodiment of the present invention is shown below. Figure 10 As shown, it includes the following steps:

[0149] S501, provides flashback alarm protection based on flashback characterization parameters;

[0150] The system calculates the backfire margin in real time and compares it with the backfire margin alarm value. When the backfire margin exceeds the backfire margin alarm value, it indicates that there is a possibility of backfire in the hydrogen-blended gas turbine, and an alarm is issued. The operator can reduce the gas turbine power or the hydrogen blending ratio as needed based on the current gas turbine operating conditions.

[0151] S502 provides flashback trip protection based on flashback characterization parameters.

[0152] Three parameters are used for flashback trip protection: flashback detection index, flashback margin, and flashback state. The flashback detection index and flashback margin are calculated indirectly using parameters such as laminar flame velocity, reactant inflow velocity, and turbulence intensity. The flashback state is calculated directly based on data generated from the three-dimensional flow net model of the combustion chamber.

[0153] The following temper protection logic is adopted, and its schematic diagram is shown below. Figure 11 As shown:

[0154] When the flashback detection index exceeds the flashback detection index threshold, a flashback trip signal is issued.

[0155] When the tempering margin exceeds the tempering margin trip value, a tempering trip signal is issued.

[0156] When a flashback occurs, a flashback trip signal is issued.

[0157] A structural diagram of a hydrogen-gas turbine ignition device according to an embodiment of the present invention is shown below. Figure 12 As shown.

[0158] The hydrogen-gas turbine flashback control device includes:

[0159] The first generation module is used to generate a combustion chamber tempering database based on the three-dimensional flow net data of the combustion chamber.

[0160] The second generation module is used to generate calculation models for combustion state characterization parameters such as flame velocity, reactant inflow velocity, and turbulence intensity based on the combustion chamber tempering database.

[0161] The third generation module is used to generate combustion chamber flashback characterization parameters based on combustion chamber combustion state characterization parameters;

[0162] The control module is used to perform backfire control on the hydrogen-mixed gas turbine based on the combustion state characterization parameters of the combustion chamber and the standard parameters of the combustion chamber backfire.

[0163] Embodiments of the present invention also provide an electronic device, a readable storage medium, and a computer program product.

[0164] A block diagram of the electronic equipment in the hydrogen-gas turbine flashback control method of one embodiment of the present invention is shown in Figure 13.

[0165] Electronic devices are intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. Electronic devices can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the embodiments of the invention described and / or claimed herein.

[0166] like Figure 13 As shown, it includes a memory 131, a processor 132, and a computer program stored in the memory 131 and capable of running on the processor 132. When the processor 132 executes the program, it implements the aforementioned hydrogen-mixed gas turbine backfire control method.

[0167] In the context of this invention, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. Machine-readable media can include, but are not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0168] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or computing systems that include middleware components (e.g., application servers), or any combination of such backend and middleware components. The components of the system can be interconnected via digital data communication (e.g., communication networks) of any form or medium. Examples of communication networks include local area networks (LANs), wide area networks (WANs), and the Internet.

[0169] Computer systems can include clients and servers. Clients and servers are generally located far apart and typically interact via communication networks. Client-server relationships are created by computer programs running on the respective computers and having a client-server relationship with each other. Servers can be cloud servers, servers in distributed systems, or servers incorporating blockchain technology.

[0170] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this invention, "a plurality of" means two or more, unless otherwise explicitly specified.

[0171] In the description of this specification, references to the terms "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., refer to a specific feature, structure, material, or characteristic described in connection with that embodiment or example that is included in at least one embodiment or example of the present invention.

[0172] Note that the above description is merely a preferred embodiment of the present invention and the technical principles employed. Those skilled in the art will understand that the present invention is not limited to the specific embodiments described herein, and various obvious changes, readjustments, and substitutions can be made without departing from the scope of protection of the present invention. Therefore, although the present invention has been described in detail through the above embodiments, the present invention is not limited to the above embodiments, and may include many other equivalent embodiments without departing from the concept of the present invention, the scope of which is determined by the scope of the appended claims.

Claims

1. A method for controlling the flashback of a hydrogen-mixed gas turbine, characterized in that, include: S1: Using a three-dimensional flow net model of the combustion chamber, the flame velocity, reactant inflow velocity, turbulence intensity, and flashback state of the hydrogen-blended gas turbine under different compressor outlet temperatures, different compressor outlet pressures, different combustion chamber inlet air flow rates, different hydrogen blending ratios, different total fuel amounts, different fuel pipeline distribution ratios, different fuel temperatures, and different fuel pressures are calculated to construct a combustion chamber flashback database. S2: Using the aforementioned combustion chamber tempering database and employing intelligent algorithms, establish a combustion chamber proxy data model and construct combustion state characterization parameters for the combustion chamber; S3: Construct tempering characterization parameters using the combustion chamber proxy data model; the tempering characterization parameters include tempering margin ξ and tempering judgment index λ. The tempering margin Calculate using the following formula: ； in, For the tempering margin, For laminar flame velocity, For turbulence intensity, The reactant inflow velocity; The tempering judgment index Calculate using the following formula: S4: Based on tempering occurrence margin A flashback control loop is constructed to limit the amount of fuel to prevent the flashback margin from shrinking further, thereby controlling flashback. Based on tempering occurrence margin Construct a hydrogen doping ratio limiting loop to control tempering by limiting the hydrogen doping ratio; Based on tempering state and tempering margin Tempering Judgment Index Construct a flashback protection circuit to implement flashback alarm and trip protection.

2. The method for controlling the flashback of a hydrogen-mixed gas turbine according to claim 1, characterized in that, In step S1, the combustion chamber flashback database of the hydrogen-blended gas turbine is calculated based on the three-dimensional flow net model of the combustion chamber, including: S101, Set the boundary conditions for the calculation of the three-dimensional flow net model of the combustion chamber; The boundary conditions calculated by the three-dimensional flow net model of the combustion chamber include compressor outlet temperature, compressor outlet pressure, combustion chamber inlet air flow rate, hydrogen blending ratio, total fuel volume, fuel pipeline distribution ratio, fuel temperature, and fuel pressure. S102, run the three-dimensional flow net model of the combustion chamber, obtain the model calculation results, and record the flame velocity, reactant inflow velocity, turbulence intensity, and tempering state; S103, through the database storage command, stores the compressor outlet temperature, compressor outlet pressure, combustion chamber inlet air flow rate, hydrogen blending ratio, total fuel, fuel pipeline distribution ratio, fuel temperature, fuel pressure, flame velocity, reactant inflow velocity, turbulence intensity, and tempering state into the combustion chamber tempering database; S104, modify the boundary conditions of different three-dimensional flow net models of the combustion chamber, and repeat the above steps.

3. The method for controlling the flashback of a hydrogen-mixed gas turbine according to claim 1, characterized in that, The intelligent algorithm described in step S2 includes machine learning.

4. The method for controlling the flashback of a hydrogen-mixed gas turbine according to claim 1, characterized in that, The combustion state characterization parameters of the combustion chamber are represented by the following function: ； in, For compressor outlet temperature, This refers to the compressor outlet pressure. This refers to the airflow rate at the combustion chamber inlet. The hydrogen doping ratio, Total fuel quantity For the fuel flow ratio of each nozzle, For fuel temperature, For fuel quantity pressure, For laminar flame velocity, The reactant inflow velocity, For turbulence intensity, It is in the tempered state.

5. The method for controlling the flashback of a hydrogen-mixed gas turbine according to claim 4, characterized in that, The function is obtained using the support vector machine regression algorithm. , , The function is obtained by using the support vector machine classification algorithm. .

6. The method for controlling the flashback of a hydrogen-mixed gas turbine according to claim 1, characterized in that, The basis for tempering state and tempering occurrence margin Tempering Judgment Index Constructing a flashback protection circuit and implementing flashback alarm and trip protection includes the following steps: When the tempering judgment index When the flashback detection index threshold is exceeded, a flashback trip signal is issued; When the tempering margin occurs When the backfire margin trip value is exceeded, a backfire trip signal is issued; When a flashback occurs, a flashback trip signal is issued.

7. A flashback control device for a hydrogen-mixed gas turbine, characterized in that, include: The first generation module is used to generate a combustion chamber tempering database based on the three-dimensional flow net data of the combustion chamber. The second generation module is used to generate a calculation model for combustion state characterization parameters of the combustion chamber based on the combustion chamber tempering database; The third generation module is used to generate combustion chamber flashback characterization parameters based on combustion chamber combustion state characterization parameters; The control module is used to perform backfire control on the hydrogen-mixed gas turbine based on the combustion state characterization parameters of the combustion chamber and the standard parameters of the combustion chamber backfire.

8. An electronic device comprising a memory and a processor, characterized in that, The processor runs a program corresponding to the executable program code by reading the executable program code stored in the memory, so as to implement the hydrogen-mixed gas turbine backfire control method as described in any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When executed by the processor, the program implements the hydrogen-mixed gas turbine flashover control method as described in any one of claims 1 to 6.

Images