Heavy-duty gas turbine low-nitrogen combustion system and control method

Abstract

The invention discloses a heavy duty gas turbine low-nitrogen combustion system and a control method, and relates to the technical field of gas turbine combustion, the system comprises a gradient aperture fuel nozzle, a self-adaptive premixing section, a dual-mode on-duty combustor and a steam dilution system; inlets of the gradient aperture fuel nozzles and the dual-mode on-duty burner are connected with the fuel distributor, the gradient aperture fuel nozzles are distributed in the circumferential direction of the head of the combustion chamber, outlets of the gradient aperture fuel nozzles are connected with the self-adaptive premixing section, the self-adaptive premixing section is connected with the combustion chamber, and the dual-mode on-duty burner is arranged in the center of the combustion chamber. A plurality of spray holes are formed in the wall surface of the gradient aperture fuel nozzle blade, and the apertures are gradually reduced along the fuel flowing direction; the self-adaptive premixing section comprises a front fuel section and a rear mixing section, the front fuel section is provided with guide vanes, and turbulent flow ribs are arranged on the inner wall of the rear mixing section. According to the control method, efficient and clean operation is achieved by obtaining operation data, digital twin model analysis and reinforcement learning optimization parameters.

Description

A low-NOx combustion system and control method for heavy-duty gas turbines Technical Field

[0001] This invention relates to the field of gas turbine combustion technology, specifically to a low-NOx combustion system and control method for heavy-duty gas turbines. Background Technology

[0002] With increasingly stringent environmental regulations, low-emission technologies for heavy-duty gas turbine combustion systems face significant challenges. While traditional lean premixed combustion technology has achieved some success in reducing NOx emissions, it still faces numerous technical bottlenecks in practical applications.

[0003] First, the design of the premixing section faces a dilemma: increasing the premixing length weakens the swirl intensity, leading to a decrease in mixing efficiency, while shortening the length easily causes uneven fuel-air mixing. Second, standby burners typically employ diffusion combustion, which, while ensuring combustion stability, creates localized high-temperature zones, becoming a major source of NOx formation. Existing improvement solutions mostly focus on single technical approaches, such as simply optimizing nozzle orifice diameter, adjusting swirler structure, or introducing steam dilution. While these measures can partially improve emission performance, they cannot fundamentally resolve the contradiction between low emissions and combustion stability. Furthermore, traditional systems perform poorly in handling rapid load changes and adaptability to multiple fuels, with limited adjustment range, failing to meet the flexible peak-shaving requirements of modern power systems. Although technologies such as micro-mixing combustion and staged combustion have shown some potential in recent years, their emission reduction effects and operational stability still need improvement due to the lack of systematic parameter synergistic optimization and intelligent control strategies. These current technological limitations severely restrict the application prospects of gas turbines in the clean energy field, urgently requiring the development of an innovative solution that can comprehensively optimize burner structural parameters and operational control strategies. Summary of the Invention

[0004] To overcome the problems of existing gas turbine combustion systems, such as the contradiction between low NOx emissions and combustion stability, insufficient fuel-air mixing uniformity, limited load adjustment range, and poor adaptability to various fuels, this invention provides a low-NOx combustion system and control method for heavy-duty gas turbines. Through the coordinated design of gradient aperture nozzles, an adaptive premixing section, a dual-mode burner, and a steam dilution system, combined with digital twin intelligent control, the emission performance, operational stability, and fuel adaptability of the combustion system are improved, achieving efficient and clean operation of the heavy-duty gas turbine.

[0005] This invention is achieved through the following technical solution: a low-NOx combustion system for a heavy-duty gas turbine, comprising a gradient aperture fuel nozzle, an adaptive premixing section, a dual-mode standby burner, and a steam dilution system; the inlets of the gradient aperture fuel nozzle and the dual-mode standby burner are connected to a fuel distributor, the gradient aperture fuel nozzle is arranged circumferentially at the head of the combustion chamber, the outlet of the gradient aperture fuel nozzle is connected to the adaptive premixing section, the adaptive premixing section is connected to the combustion chamber, the dual-mode standby burner is located at the center of the combustion chamber, and the steam dilution system is connected to the gradient aperture fuel nozzle; the blade wall of the gradient aperture fuel nozzle is provided with multiple nozzles, the diameter of which decreases sequentially along the fuel flow direction; the adaptive premixing section includes a front fuel section and a back mixing section, the front fuel section is connected to the fuel nozzle, the back mixing section is connected to the combustion chamber, the front fuel section is provided with guide vanes, and the inner wall of the back mixing section is provided with turbulence ribs, and air enters the back mixing section, mixes with the fuel, and then enters the combustion chamber.

[0006] Preferably, the plurality of nozzles are arranged in an array on the blade wall, and the angle between the axis of the nozzle and the axis of the fuel nozzle gradually decreases along the axial direction of the nozzle.

[0007] Preferably, the spray holes include large spray holes, medium spray holes and small spray holes according to their diameters. The axis of the large spray hole makes an angle of 15-25° with the axis of the nozzle, the axis of the medium spray hole makes an angle of 10-15° with the axis of the nozzle, and the axis of the small spray hole is parallel to the axis of the nozzle.

[0008] Preferably, the ratio of the number of large nozzles, medium nozzles and small nozzles is (1-3):(2-4):(1-3).

[0009] Preferably, the small nozzle is provided with a Venturi contraction section along its axial direction.

[0010] Preferably, the post-mixing section has a trumpet-shaped structure with a widening angle of 6-10° and multiple turbulence ribs arranged in a spiral.

[0011] Preferably, the dual-mode standby burner is equipped with a diffusion combustion, micro-mixing combustion mechanism and / or a pre-combustion chamber structure.

[0012] Preferably, the steam dilution system includes a heater and an annular multi-hole injector. One end of the heater is connected to the waste heat boiler via a pipeline, and the other end of the heater is connected to the annular multi-hole injector. The annular multi-hole injector is connected to a fuel pipeline, and the other end of the heater is connected to the waste heat boiler via a steam return control valve.

[0013] A control method for a low-NOx combustion system of a heavy-duty gas turbine includes the following steps: Step 1, acquiring combustion chamber operating data, including temperature field distribution, pressure fluctuation, fuel flow rate, steam injection rate, and NOx / CO emission concentration; Step 2, inputting the operating data into a pre-trained digital twin model to obtain a combustion state feature matrix; Step 3, with the objectives of minimizing NOx / CO emissions, maximizing combustion efficiency, and optimizing pressure fluctuation, combining the combustion state feature matrix, using a multi-parameter collaborative optimization algorithm based on reinforcement learning to dynamically calculate the optimal control parameters of the low-NOx combustion system of the heavy-duty gas turbine, and controlling the operating state of the low-NOx combustion system of the heavy-duty gas turbine according to the optimal control parameters.

[0014] Preferably, the combustion chamber fault state is determined by comparing the combustion state characteristic matrix with the abnormal mode library. Compared with the prior art, the present invention has the following beneficial technical effects: The heavy-duty gas turbine low-NOx combustion system provided in this application adopts a multi-stage gradient aperture fuel nozzle array design. By optimizing the aperture distribution and injection angle, the uniformity of fuel-air mixing is improved. The adaptive premixing section structure, combined with CFD-optimized turbulence elements, enhances the turbulent mixing effect and reduces pressure loss. The dual-mode standby burner design integrates diffusion combustion and micro-mixing combustion modes, which can be quickly switched according to operating conditions. The matching steam dilution system achieves intelligent adjustment of combustion temperature by precisely controlling steam parameters. Furthermore, combined with the control method, which is based on digital twin technology, the system achieves dynamic optimization and control of the combustion process by collecting operating data in real time and establishing a multi-parameter optimization model. This invention not only reduces the emission levels of pollutants such as nitrogen oxides, but also improves the operational stability, load adaptability, and fuel flexibility of the combustion system, providing an innovative overall solution for the clean and efficient operation of heavy-duty gas turbines. Attached Figure Description

[0015] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of this application and should not be regarded as a limitation of the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0016] Figure 1 is a structural diagram of the low-NOx combustion system for heavy-duty gas turbines of the present invention.

[0017] Figure 2 is a control flowchart of the low-NOx combustion system for heavy-duty gas turbines of the present invention.

[0018] In the diagram: 101, gradient aperture fuel nozzle; 102, adaptive premixing section; 103, dual-mode standby burner; 104, steam dilution system; 105, intelligent control unit. To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. The components of the embodiments of this application described and shown in the accompanying drawings can generally be arranged and designed in various different configurations.

[0019] Therefore, the following detailed description of the embodiments of this application provided in the accompanying drawings is not intended to limit the scope of the claimed application, but merely to illustrate selected embodiments of the application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without inventive effort are within the scope of protection of this application.

[0020] Referring to Figure 1, a low-NOx combustion system for a heavy-duty gas turbine includes a gradient aperture fuel nozzle 101, an adaptive premixing section 102, a dual-mode standby burner 103, and a steam dilution system 104.

[0021] The inlets of the gradient aperture fuel nozzle 101 and the dual-mode standby burner 103 are connected to the fuel distributor. The gradient aperture fuel nozzle is arranged in the circumferential position at the head of the combustion chamber. The outlet of the gradient aperture fuel nozzle 101 is connected to the adaptive premixing section 102. The adaptive premixing section 102 is connected to the combustion chamber. The dual-mode standby burner 103 is located in the center of the combustion chamber. The steam dilution system 104 is connected to the gradient aperture fuel nozzle 101.

[0022] After the fuel enters the system, the distribution valve controlled by the intelligent control unit 105 divides it into two paths: most of the fuel enters the gradient aperture fuel nozzle 101, and a small portion of the fuel is supplied to the dual-mode duty burner 103 to stabilize the flame.

[0023] Air enters the adaptive premixing section 102 and forms a swirling flow through adjustable guide vanes to premix with the fuel input from the gradient aperture fuel nozzle.

[0024] Fuel is ejected through large, medium, and small diameter nozzles with different offset angles, forming a three-dimensional fuel jet. The steam dilution system 104 injects steam upstream of the fuel, initially mixing it and providing cooling. Fuel, steam, and high-speed swirling air converge in the premixing section. Internal turbulence ribs and a gradually expanding structure greatly enhance the turbulent mixing effect, forming a uniform premixed gas. This premixed gas enters the combustion chamber for efficient and clean combustion. The dual-mode standby burner is located in the center, ensuring the flame does not extinguish when operating conditions change in the main combustion zone.

[0025] The intelligent control unit 105 monitors the combustion status in real time through sensors (temperature, pressure, emissions) throughout the system, and sends commands to the fuel distribution valve, steam regulating valve, premix section guide vanes and shift burner mode switching mechanism to achieve dynamic optimization control.

[0026] In some embodiments, the blade wall of the gradient aperture fuel nozzle 101 is provided with a plurality of nozzles, which are arranged in an array along the wall. The diameter of the nozzles decreases sequentially along the fuel flow direction, and the diameter of the nozzles in each row along the radial direction of the nozzle in the array is the same.

[0027] In this embodiment, the nozzles are divided into three groups according to their diameters. Along the fuel flow direction, the diameters of the three groups of nozzles increase sequentially, with the nozzle closest to the upstream being the smallest.

[0028] In some embodiments, the angle between the axis of the nozzle and the axis of the fuel nozzle gradually decreases along the axial direction of the nozzle.

[0029] The three sets of nozzles have diameters of large, medium, and small, respectively. The axis of the large nozzle forms an angle of 15-25° with the nozzle axis, the axis of the medium nozzle forms an angle of 10-15° with the nozzle axis, and the axis of the small nozzle is parallel to the nozzle axis. The purpose of the large nozzle is to allow the fuel to be injected further into the airflow field, avoiding all fuel from concentrating in the central area and causing uneven mixing. The medium diameter acts as a transition, filling the area between the large and small diameter injection ranges, making the circumferential fuel distribution more uniform. The small nozzle injects directly along the centerline to ensure fuel supply and flame stability in the central area of ​​the combustion chamber. This gradient offset design works together to achieve rapid and uniform mixing of fuel and air in the combustion chamber, which is key to achieving low nitrogen oxide (NOx) combustion.

[0030] Optionally, the small nozzle is provided with a Venturi contraction section in the axial direction, and the contraction ratio of 1.2:1 ensures uniform distribution.

[0031] The gradient aperture fuel nozzle body is made of Inconel 718 alloy substrate and covered with a 200μm thick 8YSZ ceramic coating (temperature resistance 1873K). It achieves independent and precise distribution of three stages of fuel through a piezoelectric micro-valve (response time 10ms).

[0032] Optionally, the ratio of the number of large nozzles, medium nozzles and small nozzles is (1-3):(2-4):(1-3).

[0033] In some embodiments, the adaptive premixing section 102 adopts a segmented structure, including a front fuel section and a rear mixing section. The front fuel section is connected to the fuel nozzle, and the rear mixing section is connected to the combustion chamber. The inner wall of the rear mixing section is provided with baffles. Air enters the rear mixing section, mixes with the fuel, and then enters the combustion chamber.

[0034] Optionally, the pre-mixing section is a 350mm diameter section with an inner diameter of 200mm to ensure stable flow; the post-mixing section is a trumpet-shaped structure with a divergence angle of 6-10° and an outlet diameter of 220mm.

[0035] The inner wall of the post-mixing section is evenly distributed with turbulence ribs. The turbulence ribs are triangular in structure and 2.5 mm high, which improve the turbulent mixing effect and reduce pressure loss.

[0036] The premixing section is made of Inconel 625 alloy and its length can be infinitely adjusted from 500 to 800 mm via a hydraulic mechanism (response <100ms), with the mixing non-uniformity controlled within 5%.

[0037] The adaptive premixing section is equipped with an adjustable guide vane structure, the adjustment angle of which is 15-45°. The adjustable guide vane is steplessly adjustable via a hydraulic or electric actuator, with an adjustment response time of less than 100ms.

[0038] The adaptive premixing section has an adjustable length structure with a length adjustment range of 500-800 mm.

[0039] In some embodiments, the dual-mode standby burner is configured with diffusion combustion and micro-mixing combustion mechanisms to achieve both diffusion combustion and micro-mixing combustion modes.

[0040] In diffusion combustion mode, a 6-hole nozzle with a diameter of 2.0 mm is used to inject the mixed fuel; in micro-mixing combustion mode, a 12-channel premixed nozzle with an orifice diameter of 1.0 mm is used to inject the mixed fuel.

[0041] This dual-mode burner is equipped with a pneumatic rotary valve for rapid response switching (switching time <80ms) and uses SiC ceramic high-temperature resistant material (temperature resistance 1873K). It can achieve smooth switching of combustion modes according to operating conditions (transition time <0.5s). The diffusion mode is used for stable combustion at low loads, and the micro-mixing mode is used for low-emission conditions at high loads. Both modes are optimized through CFD design to ensure stable combustion.

[0042] Optionally, the dual-mode shift burner is equipped with a pre-combustion chamber structure, which adopts a porous media structure with a porosity of 50-70%.

[0043] In some embodiments, the steam dilution system 104 includes a heater and an annular orifice injector. One end of the heater is connected to a waste heat boiler via a pipeline, and the other end of the heater is connected to the annular orifice injector, which is connected to a fuel pipeline.

[0044] Optionally, the other end of the heater can be connected to the waste heat boiler via a steam reflux control valve.

[0045] The steam dilution system 104 extracts saturated steam at 1.8 MPa from the waste heat boiler and heats it to a superheated state of 420 ± 5 K via a 3 kW electric heater. A PT100 temperature-pressure composite sensor (accuracy ± 0.5%) monitors steam parameters in real time, providing feedback to the control system. The steam flow rate is precisely regulated by a PID control valve (response time 50 ms) and then injected into the fuel pipeline via a ring-shaped multi-hole injector (16 evenly distributed 3 mm diameter nozzles) located 1.5 m upstream. After being fully mixed with the fuel, the steam enters the combustion chamber to participate in the combustion reaction. Unreacted steam is returned to the waste heat boiler for recycling via a return pipeline. Throughout this process, a mass flow meter (accuracy ± 0.5%) continuously monitors the steam / fuel mass ratio (1.6-2.2), forming a closed-loop control system with the PID control valve to ultimately ensure the uniformity of the combustion chamber temperature field (temperature non-uniformity < 30 K).

[0046] In some embodiments, the intelligent control unit 105 uses a Siemens S7-1500 PLC (control cycle 0.5ms) as the core controller, equipped with a 16-channel high-speed data acquisition module (sampling rate 10kHz) and a complete signal conditioning circuit. Through a GPU-accelerated digital twin model (update frequency 50Hz) and the NSGA-II multi-objective optimization algorithm, it realizes real-time optimization of combustion parameters (NOx, CO, combustion efficiency, etc.).

[0047] The following is a detailed description of the operation of the low-NOx combustion system for heavy-duty gas turbines in this application.

[0048] Fuel is injected into the premixing section 102 through gradient aperture nozzles 101 at an optimized flow ratio. It is fully mixed with the airflow organized by adjustable guide vanes under the action of turbulence ribs before entering the combustion chamber. The dual-mode standby burner 103 automatically switches the working mode (diffusion / micro-mixing mode) according to the load signal (such as below 30% of the rated load). The steam dilution system 104 injects superheated steam at 420±5K at a steam / fuel mass ratio of 1.6-2.2 through closed-loop control. The intelligent control unit 105 collects and analyzes multiple operating parameters such as temperature, pressure, and emissions in real time through a digital twin model, and updates the control command every 100ms to ensure that the system always maintains the best working state (NOx<15mg / m³@15%O2) during load changes (±5% / min) and fuel switching (natural gas / hydrogen).

[0049] Correspondingly, referring to Figure 2, this application also provides a control method for a low-NOx combustion system of a heavy-duty gas turbine, including the following steps: Step 1: Obtain the operating data of the combustion chamber, including temperature field distribution, pressure fluctuation, fuel flow rate, steam injection rate and NOx / CO emission concentration; collect the operating data through a sensor array arranged at key locations in the combustion chamber, wherein the sensor array includes various types of sensors such as high-temperature thermocouples, dynamic pressure sensors, and optical detection probes.

[0050] Step 2: Preprocess the operating data and construct a dataset based on the preprocessed operating data; use data filtering and normalization techniques to fuse multi-source sensor data, extract key features of combustion stability, emission characteristics and thermal efficiency, and form a dynamically updated combustion state feature matrix.

[0051] The combustion state feature matrix is ​​a real-time dynamically updated multi-dimensional dataset. By fusing data from multiple sources such as temperature, pressure, flow rate, and emissions sensors, and employing spatiotemporal correlation and normalization processing, it forms a structured feature that comprehensively characterizes the operating state of the combustion system. This matrix includes both the statistical characteristics of the original parameters (such as mean and fluctuation) and extracts key correlation indicators (such as the NOx-temperature gradient relationship), providing standardized input for the digital twin model. It is the core data foundation for realizing intelligent monitoring, prediction, and optimization of the combustion process.

[0052] Step 3: Construct a digital twin model. Train the digital twin model using CFD simulation data and historical operating data of the combustion chamber. The trained model outputs a combustion state feature matrix, including combustion stability index, predicted NOx / CO emission values, and thermal efficiency parameters. Step 4: Input the preprocessed operating data from Step 2 into the trained model to predict the combustion state feature matrix of the combustion chamber. Compare the combustion state feature matrix with the abnormal mode library to determine the fault state of the combustion chamber, and realize early warning and fault diagnosis of flameout, backfire, combustion instability, and local high temperature.

[0053] Step 5: With the objectives of minimizing NOx / CO emissions, maximizing combustion efficiency, and optimizing pressure fluctuations, a multi-parameter collaborative optimization algorithm based on the combustion state feature matrix is ​​used to dynamically calculate the optimal control parameters of the low-NOx combustion system of the heavy-duty gas turbine, including the fuel distribution ratio of gradient aperture nozzles, steam dilution system injection parameters, and shift burner mode switching strategy. During the optimization process, an adaptive weighting mechanism is introduced to dynamically adjust the priority of each objective according to the operating conditions.

[0054] Step 6: Control the operation of the low-NOx combustion system of the heavy-duty gas turbine according to the optimal control parameters.

[0055] The optimal control parameters are adjusted through the actuator, including: adjusting the fuel distribution ratio of the gradient orifice nozzle; controlling the injection volume and temperature of the steam dilution system; switching the operating mode of the shift burner; synchronously collecting the adjusted operating data and comparing it with the predicted target. If the deviation exceeds the threshold, iterative optimization is triggered until the system reaches the steady-state optimal operating state.

[0056] Monitor the fuel distribution ratio of each stage of the gradient orifice nozzle, and dynamically adjust the fuel supply of large, medium and small orifice nozzles according to load changes.

[0057] Adjust the temperature to 15-30°C when using natural gas fuel; adjust it to 30-45°C when using hydrogen-blended fuel.

[0058] The system automatically switches the duty combustion mode according to load changes: diffusion combustion mode is used during startup and low load stages; micro-hybrid combustion mode is switched to medium load stages; and the main burner operates in conjunction with the system during high load stages.

[0059] This invention provides a control method for a low-NOx combustion system in a heavy-duty gas turbine. Through the coordinated design of gradient aperture nozzles and an adaptive premixing section, the mixing effect of fuel and air is improved. The combination of a dual-mode standby burner and a steam dilution system ensures combustion stability while achieving ultra-low pollutant emissions. A digital twin-based intelligent control system enhances the system's adaptability under different operating conditions and expands the load adjustment range. The system exhibits good multi-fuel compatibility, adapting to the combustion requirements of various clean fuels. The modular structural design improves the system's maintainability and economy, providing a reliable technical guarantee for the clean and efficient operation of the gas turbine.

[0060] Example 1: A low-NOx combustion system for a heavy-duty gas turbine includes: a gradient aperture fuel nozzle with a three-stage aperture combination design, wherein a 1.8mm large aperture is offset by 18° to enhance fuel penetration depth, a 1.2mm medium aperture is offset by 12° to improve circumferential distribution, and a 1.0mm small aperture is arranged axially to ensure uniform mixing. The three apertures are optimally configured in a ratio of 2:3:2. The nozzle body is made of high-temperature resistant nickel-based alloy material to ensure long-term reliability in high-temperature environments.

[0061] The adaptive premixing section adopts a segmented structural design. The front section is a 350mm long section with a constant diameter and an inner diameter of 200mm. The rear section adopts a 6° gradually expanding angle design, and the outlet diameter is expanded to 220mm. The inner wall is equipped with 2.5mm high triangular turbulence ribs. The ribs are evenly distributed with a 30° helical angle, which effectively enhances the turbulent mixing effect while controlling pressure loss.

[0062] The dual-mode standby burner integrates two working modes: a 6-hole diffusion combustion nozzle and a 12-channel micro-mixer burner. It uses a high-performance pneumatic actuator to switch combustion modes, with the switching time controlled within 80ms, ensuring combustion stability under load changes. Both modes have been optimized by CFD design.

[0063] The steam dilution system is designed to operate at a pressure of 1.8 MPa. A precise temperature control system maintains the steam temperature within the range of 420 ± 5 K. A mass flow meter monitors the steam and fuel flow rates in real time, and a closed-loop control algorithm precisely adjusts the steam / fuel mass ratio within an optimized range of 1.6-2.2. The steam dilution system is equipped with a safety relief valve (operating pressure 2.0 MPa) to prevent overpressure in the steam pipeline.

[0064] The intelligent control system uses a SIEMENS S7-1500 series PLC as the core controller, is equipped with a 16-channel high-speed data acquisition module, and has a control cycle of 0.5ms. The system integrates a predictive model based on neural network algorithms, which can optimize operating parameters in real time and communicate with the power plant's DCS system via the Modbus-TCP protocol.

[0065] In practical applications, this embodiment achieves stable NOx emissions below 15 mg / m³ (@15% O2) and CO emissions below 8 mg / m³; combustion efficiency reaches 99.6%; load adjustment response time is shortened to 1.5 seconds (50%-100% load change), and its overall performance is superior to similar traditional combustion systems.

[0066] Example 2 is an optimization based on Example 1.

[0067] A low-NOx combustion system for heavy-duty gas turbines includes: gradient aperture fuel nozzles, which retain the original three-stage gradient aperture nozzle array (large / medium / small aperture), and adopt SiC-Si3N4 ceramic matrix composite material to withstand higher combustion temperatures (1873K). A hydrogen fuel mixing interface is added, and a Venturi mixer is used to ensure uniform mixing of natural gas and hydrogen (non-uniformity <3%). The offset design of large aperture 20°±2° and medium aperture 12°±1° is maintained. At the same time, a dynamic calibration function of flow coefficient in hydrogen mode is added to ensure compatibility with the original system's fuel distribution logic.

[0068] The adaptive premixing section features a honeycomb microstructure surface treatment on its inner wall to enhance turbulence intensity.

[0069] The dual-mode standby burner adds a pre-combustion chamber mode as an extended option for high hydrogen (>30% H2) conditions. It uses a porous medium with 60% porosity to suppress backfire, and the switching mechanism still maintains an 80ms response speed. Operating data shows that it can ensure combustion stability under both pure natural gas and 50% hydrogen mixed combustion conditions.

[0070] The steam dilution system integrates a laser oxygen analyzer (accuracy ±0.2 vol%), which merges with existing temperature / pressure sensor data to dynamically adjust the steam / nitrogen dilution ratio (1.5-2.5) to stably control the oxygen concentration in the combustion chamber at 14.5 ± 0.5 vol%, serving as a supplementary strategy to the original steam injection control.

[0071] The intelligent control system adds a hydrogen combustion sub-model to the original digital twin framework, integrates the hydrogen combustion mechanism including 21 elementary reactions, realizes online model updates (cycle <5s) through edge computing nodes, and runs in collaboration with the original CFD simulation database to ensure the prediction accuracy of hydrogen-doped conditions.

[0072] This embodiment optimizes a high-hydrogen fuel combustion system, achieving NOx emissions of <12 mg / m³ and CO emissions of <5 mg / m³ under 50% hydrogen blending conditions; the load regulation range is extended to 15-110%; the hydrogen fuel switching process is smooth, with a transition time of <2 minutes. The system is suitable for renewable energy-to-hydrogen co-generation scenarios, providing an important solution for the development of gas turbine technology under the goal of carbon neutrality.

[0073] Example 3 This application also provides a control system for a low-NOx combustion system of a heavy-duty gas turbine, comprising: a data acquisition module for acquiring combustion chamber operating data, including temperature field distribution, pressure fluctuation, fuel flow rate, steam injection rate, and NOx / CO emission concentration; a combustion state module for inputting the operating data into a pre-trained digital twin model to obtain a combustion state feature matrix; and an optimization module for dynamically calculating the optimal control parameters of the low-NOx combustion system of the heavy-duty gas turbine using a multi-parameter collaborative optimization algorithm of reinforcement learning, with the objectives of minimizing NOx / CO emissions, maximizing combustion efficiency, and optimizing pressure fluctuation, in conjunction with the combustion state feature matrix, and controlling the operating state of the low-NOx combustion system of the heavy-duty gas turbine according to the optimal control parameters.

[0074] It should be noted that, in the several embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of modules is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple modules may be combined or integrated into another device, or some features may be ignored or not executed. The modules described as separate components may or may not be physically separated. The components shown as modules may be one or more physical units, that is, they may be located in one place or distributed in multiple different places. Some or all of the modules can be selected to achieve the purpose of the solution in this embodiment according to actual needs.

[0075] Furthermore, in the various embodiments of the present invention, the modules can be integrated into one processing unit, or each module can exist physically separately, or two or more modules can be integrated into one unit. The integrated unit described above can be implemented in hardware or as a software functional unit.

[0076] An electronic device provided in this application includes a memory and a processor. The memory stores a computer program, and when the processor executes the computer program, it implements the steps of the control method for the low-NOx combustion system of a heavy-duty gas turbine as described in any of the above embodiments.

[0077] Another electronic device provided in this application embodiment may further include: an input port connected to a processor for transmitting multimodal data collected by an external acquisition device to the processor; a display unit connected to the processor for displaying the processor's processing results to the outside world; and a communication module connected to the processor for enabling communication between the electronic device and the outside world. The display unit may be a display panel, a laser scanning display, etc.; the communication method adopted by the communication module includes, but is not limited to, Mobile High Definition Link (HML), Universal Serial Bus (USB), High Definition Multimedia Interface (HDMI), and wireless connection (including Wi-Fi, Bluetooth, Bluetooth Low Energy, and IEEE 802.11s-based communication technology).

[0078] This application provides a computer-readable storage medium storing a computer program. When executed by a processor, the computer program implements the steps of the control method for a low-NOx combustion system of a heavy-duty gas turbine as described in any of the above embodiments.

[0079] For descriptions of the control system, electronic equipment, and computer-readable storage medium of the heavy-duty gas turbine low-NOx combustion system provided in this application's embodiments, please refer to the detailed description of the corresponding parts in the control method of the heavy-duty gas turbine low-NOx combustion system provided in this application's embodiments; they will not be repeated here. Furthermore, parts of the technical solutions provided in this application that are consistent with the implementation principles of corresponding technical solutions in the prior art have not been described in detail to avoid excessive elaboration.

[0080] The above content is only for illustrating the technical concept of the present invention and should not be construed as limiting the scope of protection of the present invention. Any modifications made to the technical solution based on the technical concept proposed in this invention shall fall within the scope of protection of the claims of this invention.

Claims

1. A low-NOx combustion system for a heavy-duty gas turbine, characterized in that, The system includes a gradient aperture fuel nozzle, an adaptive premixing section, a dual-mode standby burner, and a steam dilution system. The inlets of the gradient aperture fuel nozzle and the dual-mode standby burner are connected to a fuel distributor. The gradient aperture fuel nozzle is positioned circumferentially at the head of the combustion chamber, and its outlet is connected to the adaptive premixing section, which is connected to the combustion chamber. The dual-mode standby burner is located at the center of the combustion chamber, and the steam dilution system is connected to the gradient aperture fuel nozzle. The blade wall of the gradient aperture fuel nozzle has multiple nozzles, with the diameter of each nozzle decreasing sequentially along the fuel flow direction. The adaptive premixing section includes a pre-fuel section and a post-mixing section. The pre-fuel section is connected to the fuel nozzle, and the post-mixing section is connected to the combustion chamber. The pre-fuel section has guide vanes, and the inner wall of the post-mixing section has turbulence ribs. Air enters the post-mixing section, mixes with the fuel, and then enters the combustion chamber.

2. The heavy-duty gas turbine low-NOx combustion system according to claim 1, characterized in that, The plurality of nozzles are arranged in an array on the blade wall, and the angle between the axis of the nozzle and the axis of the fuel nozzle gradually decreases along the axial direction of the nozzle.

3. The heavy-duty gas turbine low-NOx combustion system according to claim 1, characterized in that, The nozzles are classified into large nozzles, medium nozzles, and small nozzles according to their diameter. The axis of the large nozzle is at an angle of 15-25° with the axis of the nozzle, the axis of the medium nozzle is at an angle of 10-15° with the axis of the nozzle, and the axis of the small nozzle is parallel to the axis of the nozzle.

4. The heavy-duty gas turbine low-NOx combustion system according to claim 3, characterized in that, The ratio of the number of large nozzles, medium nozzles and small nozzles is (1-3):(2-4):(1-3).

5. A low-NOx combustion system for a heavy-duty gas turbine according to claim 3, characterized in that, The small nozzle is provided with a Venturi contraction section along its axis.

6. A low-NOx combustion system for a heavy-duty gas turbine according to claim 1, characterized in that, The post-mixing section has a trumpet-shaped structure with a widening angle of 6-10° and multiple turbulence ribs arranged in a spiral.

7. A low-NOx combustion system for a heavy-duty gas turbine according to claim 1, characterized in that, The dual-mode standby burner is equipped with a diffusion combustion, micro-mixing combustion mechanism and / or a pre-combustion chamber structure.

8. A heavy-duty gas turbine low-NOx combustion system according to claim 1, characterized in that, The steam dilution system includes a heater and an annular multi-hole injector. One end of the heater is connected to the waste heat boiler via a pipeline, and the other end of the heater is connected to the annular multi-hole injector. The annular multi-hole injector is connected to the fuel pipeline, and the other end of the heater is connected to the waste heat boiler via a steam return control valve.

9. A control method for a low-NOx combustion system in a heavy-duty gas turbine, characterized in that, Includes the following steps: Step 1: Acquire combustion chamber operating data, including temperature field distribution, pressure fluctuation, fuel flow rate, steam injection rate, and NOx / CO emission concentration; Step 2: Input the operating data into a pre-trained digital twin model to obtain the combustion state feature matrix; Step 3: With the objectives of minimizing NOx / CO emissions, maximizing combustion efficiency, and optimizing pressure fluctuation, combine the combustion state feature matrix and use a multi-parameter collaborative optimization algorithm based on reinforcement learning to dynamically calculate the optimal control parameters of the heavy-duty gas turbine low-NOx combustion system, and control the operating state of the heavy-duty gas turbine low-NOx combustion system according to the optimal control parameters.

10. The control method for a low-NOx combustion system of a heavy-duty gas turbine according to claim 9, characterized in that, The combustion chamber fault status is determined by comparing the combustion state feature matrix with the abnormal mode library.

Images