A low specific speed centrifugal compressor adapted to a hydrogen-containing fuel gas turbine power generation system and an optimization method thereof

Abstract

The present application relates to gas turbine power generation technology field, especially to a kind of low specific speed centrifugal compressor of adaptation hydrogen-containing fuel gas turbine power generation system and its optimization method. Including: meridional flow passage component, impeller and blade assembly, adaptive processing casing assembly, the meridional flow passage component, impeller and blade assembly, adaptive processing casing assembly three maintain coaxial settings, jointly form closed booster flow field, realize the adaptation of hydrogen-containing fuel gas turbine power generation system. Three synergies from structural level solve the core pain points of the stability of existing compressor in hydrogen-containing fuel system, the low efficiency and poor adaptability, provide efficient and stable boost basis for hydrogen-containing fuel gas turbine power generation system.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of gas turbine power generation technology, and particularly relates to a low specific speed centrifugal compressor suitable for a hydrogen-containing fuel gas turbine power generation system and an optimization method thereof. BACKGROUND

[0002] In the hydrogen-containing fuel gas turbine power generation system, the compressor as a core component directly affects the stability and efficiency of the whole machine. In the prior art, the compressor has the following problems:

[0003] Insufficient stability: non-axisymmetric flow channel, inlet and outlet flow distortion, which easily leads to compressor instability and large pressure fluctuation;

[0004] Low efficiency: under small flow conditions, the proportion of tip clearance to blade height increases, which leads to significant increase in tip leakage loss, secondary flow loss and boundary layer loss, and it is difficult to balance efficiency and stability margin;

[0005] Poor adaptability: the low specific speed compressor is difficult to match the power demand of the hydrogen-containing fuel gas turbine power generation device (such as a 60kW level system) due to immature expansion stability and efficiency design technology under multiple working conditions.

[0006] In addition, the special properties of hydrogen-containing fuel and the complex operating conditions of the gas turbine power generation system further exacerbate the performance shortcomings of the existing centrifugal compressor. The hydrogen-containing fuel has high combustion speed and high flame temperature, which puts higher requirements on the stability and load capacity of the compressor. At the same time, factors such as non-symmetrical flow channel of the volute and flow distortion of the inlet and outlet, easily lead to compressor instability, and further affect the normal operation of the power generation system.

[0007] In summary, it is urgent to develop a low specific speed centrifugal compressor suitable for a hydrogen-containing fuel gas turbine power generation system and an optimization method thereof, which effectively solves the stability, efficiency and adaptability problems of the existing compressor. SUMMARY

[0008] Therefore, the present application aims to provide a low specific speed centrifugal compressor suitable for a hydrogen-containing fuel gas turbine power generation system and an optimization method thereof, which effectively solves the stability, efficiency and adaptability problems of the existing compressor.

[0009] According to a first aspect of an embodiment of the present application, a low specific speed centrifugal compressor suitable for a hydrogen-containing fuel gas turbine power generation system is provided, comprising: a meridian flow channel assembly, which is a fixed air flow passage frame, forms a continuous flow channel for air flow, an impeller and blade assembly, which is a rotating supercharging component, is arranged inside the meridian flow channel assembly, is coaxially assembled with the meridian flow channel assembly and maintains a preset gap therebetween, so as to supercharge the air flow entering the meridian flow channel assembly by rotation, and an adaptive processing casing assembly, which is a flow field regulation component, is arranged outside the meridian flow channel assembly, is rigidly connected with the meridian flow channel assembly and coaxially assembled, and is correspondingly arranged with the impeller and blade assembly on the inner side and maintains an adjustable gap, so as to regulate the air flow state in real time; the meridian flow channel assembly, the impeller and blade assembly and the adaptive processing casing assembly are coaxially arranged, together form a closed supercharged flow field, and realize the adaptation to the hydrogen-containing fuel gas turbine power generation system.

[0010] Further, the meridian flow channel assembly comprises:

[0011] The meridian flow channel assembly comprises, in sequence along the air flow direction, an inlet section, an impeller section, a diffuser section and an outlet section, each section forming a continuous diverging flow channel;

[0012] The inlet section is rigidly connected with an air inlet pipeline through a flange;

[0013] The impeller section is a cylindrical cavity, the inner wall of which maintains a preset initial gap with the impeller blade tip, and is connected with the inlet section through a smooth transition curved surface;

[0014] The diffuser section has a flow channel width greater than that of the inlet section, the inner wall of which is fixedly installed with diffuser blades, and the top of the blade maintains a regulation gap with the inner wall of the adaptive processing casing;

[0015] The outlet section is a diffusion type structure, is smoothly connected with the end of the diffuser section, and is connected with a combustion chamber air inlet pipeline through a flange.

[0016] Further, the meridian flow channel assembly further comprises:

[0017] The entire meridian flow channel has a preset curvature radius and a meridian surface inclination angle, and each section is coaxially arranged.

[0018] Further, the impeller and blade assembly comprises:

[0019] The impeller is integrally milled from high-strength alloy, the hub is rigidly connected with a compressor main shaft through a key groove, and the main shaft is supported at both ends through a bearing seat;

[0020] The blade root is connected with the tenon groove of the impeller rim through a dovetail tenon, the blade has a preset sweep angle, and the top of the blade maintains a preset initial gap with the inner wall of the adaptive processing casing;

[0021] The impeller and the blade assembly are integrally located in the impeller section of the meridian flow channel.

[0022] Further, the self-adaptive processing casing assembly comprises a casing body which is made of cast iron precision casting and has a ring sleeve structure, and is rigidly connected with the shell flange of the meridian flow channel through bolts.

[0023] A plurality of annular movable guide vanes are uniformly distributed on the inner wall of the casing inlet section, the roots are hinged to the casing body through micro shafts, the ends are connected with the micro hydraulic push rod ball hinge of the actuator through the connecting rod mechanism, and the shafts can rotate within a preset angle range.

[0024] The radial adjustable gap mechanism is in the form of an annular slider, is embedded in the inner wall groove of the casing near the impeller blade tip, the inner side of the slider corresponds to the blade tip, the outer side is slidably connected with the casing body through elastic guide columns, and is rigidly connected with the output end of another group of micro hydraulic push rods, so that the adjustment of the blade tip gap can be realized.

[0025] A plurality of piezoelectric pressure sensors are uniformly embedded between the impeller outlet and the diffuser inlet of the inner wall of the casing, the sensor probe is flush with the inner wall of the flow channel, the signal line is led out through the threading hole of the casing body and is electrically connected with the external controller.

[0026] Two groups of micro hydraulic push rods are respectively used to drive the annular movable guide vanes and the radial adjustable gap mechanism, are fixedly installed on the bracket on the outer wall of the casing, the bracket is welded with the casing, and the push rod control signal line is electrically connected with the controller. The meridian flow channel assembly, the impeller and blade assembly, and the self-adaptive processing casing assembly are coaxially arranged, together form a closed pressurized flow field, and realize the adaptation of the hydrogen-containing fuel gas turbine power generation system.

[0027] According to the second aspect of the embodiment of the present application, a low specific speed centrifugal compressor optimization method for adapting a hydrogen-containing fuel gas turbine power generation system is provided, which is applied to the low specific speed centrifugal compressor for adapting the hydrogen-containing fuel gas turbine power generation system.

[0028] The operation parameters of the centrifugal compressor in the hydrogen-containing fuel gas turbine power generation system are monitored in real time; the operation parameters include but are not limited to the flow, pressure ratio, efficiency, temperature, pressure fluctuation, and power demand operation parameters of the power generation system monitored at different positions of the compressor.

[0029] The sensor fusion algorithm is used to fuse the flow, pressure ratio, efficiency, temperature, pressure fluctuation, and power demand operation parameters of the power generation system monitored at different positions of the compressor by using the preset distributed sensor network, so as to obtain the fused operation parameters.

[0030] Adopting fuzzy logic algorithm, the fused running parameters are compared and analyzed with preset standard parameter range, when exceeding the standard parameter range, the optimization process is started.

[0031] Further, the adopting fuzzy logic algorithm, the fused running parameters are compared and analyzed with preset standard parameter range, when exceeding the standard parameter range, the optimization process is started, including:

[0032] Taking the pressure fluctuation in the fused running parameters as the core representation parameter, through the fuzzy logic algorithm, it is compared with the preset stability standard parameter range, when the pressure fluctuation exceeds the first range, it is determined that the compressor has the problem of insufficient stability, triggering the preset first rule group;

[0033] Taking the efficiency and flow in the fused running parameters as the joint representation parameter, through the fuzzy logic algorithm, it is compared with the preset efficiency standard parameter surface, when the actual running point deviates from the standard surface by more than the first threshold value for a continuous preset number of sampling periods, the second rule group is triggered;

[0034] Taking the power demand of the power generation system and the actual output power of the compressor in the fused running parameters as the core parameters, combining the efficiency and the preset surge margin to construct a three-dimensional adaptability evaluation space, the Euclidean distance from the current running point to the standard adaptation surface is calculated through the fuzzy logic algorithm;

[0035] When the Euclidean distance exceeds the preset second threshold value, the third rule group is triggered.

[0036] Further, the taking the efficiency and flow in the fused running parameters as the joint representation parameter, through the fuzzy logic algorithm, it is compared with the preset efficiency standard parameter surface, when the pressure fluctuation exceeds the first range, it is determined that the compressor has the problem of insufficient stability, triggering the preset first rule group, including:

[0037] Taking the efficiency and flow in the fused running parameters as the joint representation parameter, through the fuzzy logic algorithm, it is compared with the preset efficiency standard parameter surface, when the pressure fluctuation exceeds the first range, a model predictive control algorithm is adopted to control the self-adaptive processing casing assembly, the flow change trend in the flow passage is predicted according to the real-time pressure fluctuation, and the angle or cross-sectional area of the non-axisymmetric flow passage and the inlet and outlet guide vane is automatically adjusted;

[0038] The active control technology based on neural network is introduced, according to the real-time monitored pressure fluctuation signal, through the learning and prediction ability of neural network, the control parameters of active vortex control or active airflow injection are automatically adjusted.

[0039] Further, the efficiency and flow in the fused operating parameter are taken as the joint representation parameters, and the fuzzy logic algorithm is used to compare them with the preset efficiency standard parameter surface, when the actual operating point deviates from the standard surface by more than the first threshold value for a continuous preset number of sampling periods, the second rule set is triggered, including:

[0040] The efficiency and flow in the fused operating parameter are taken as the joint representation parameters, and the fuzzy logic algorithm is used to compare them with the preset efficiency standard parameter surface, when the actual operating point deviates from the standard surface by more than the first threshold value for a continuous preset number of sampling periods, the second rule set is triggered, including:

[0041] Further, the optimization process further includes:

[0042] The optimized compressor model is simulated and analyzed by using computational fluid dynamics software, and the uncertainty of the simulation result is evaluated by using a data-driven uncertainty quantification algorithm;

[0043] The reinforcement learning algorithm is used to automatically adjust the optimization parameters according to the simulation results and uncertainty evaluation, and if the expected optimization target is not reached, the simulation and adjustment process is repeated until the expected effect is achieved;

[0044] At the same time, a compressor performance database is established, and a knowledge graph algorithm is used to associate and analyze the operating parameters and optimization strategies before and after each optimization, to mine potential optimization directions and rules, and to provide a reference for subsequent optimization. The technical scheme provided by the embodiments of the application can include the following beneficial effects:

[0045] The present application realizes the collaborative optimization of the structure through the coaxial arrangement of the meridian flow channel assembly, the impeller and blade assembly, and the self-adaptive processing casing assembly, and the closed pressurization flow field design: the continuous gradual expansion flow channel of the meridian flow channel ensures smooth airflow, reduces the basic flow loss; the high-strength alloy integral forming and preset gap design of the impeller and blade improve the rotating supercharging efficiency and structural stability; the self-adaptive processing casing assembly is arranged around and adjusts the gap and flow field in real time, and can specifically suppress the instability problem caused by the flow distortion of the asymmetric flow channel, the inlet and outlet; the three cooperate to solve the core pain points of the existing compressor in the hydrogen-containing fuel system, such as insufficient stability, low efficiency and poor adaptability, from the structural level, and provide an efficient and stable pressurization basis for the hydrogen-containing fuel gas turbine power generation system.

[0046] Further, by monitoring the operating parameters of multiple parts of the compressor in real time and processing through a sensor fusion algorithm, the noise interference of single-point data is eliminated, and comprehensive and accurate fusion parameters are obtained; then, the fusion parameters are compared with the preset standard by using a fuzzy logic algorithm, which can accurately identify problems such as insufficient stability, low efficiency or poor adaptability and trigger the optimization process, solving the limitations of single-parameter monitoring and judgment. The method can quickly respond to the complex working condition changes of the hydrogen-containing fuel gas turbine power generation system, and through the targeted start of the optimization process, the state of the compressor is real-time regulated, effectively improving its stability, efficiency and adaptability to system power demand in a wide range of conditions, providing dynamic optimization guarantee for the efficient and stable operation of the hydrogen-containing fuel power generation system.

[0047] It should be understood that the above general description and the following detailed description are only exemplary and explanatory, and cannot limit the present application. BRIEF DESCRIPTION OF DRAWINGS

[0048] The accompanying drawings, which are incorporated into and form part of the specification, illustrate an embodiment consistent with the present application and, together with the description, serve to explain the principles of the application.

[0049] Figure 1 is a schematic diagram of a low specific speed centrifugal compressor of a hydrogen-containing fuel gas turbine power generation system adapted by multi-modal data fusion according to an exemplary embodiment;

[0050] Figure 2 is a schematic diagram of an optimization method of a low specific speed centrifugal compressor of a hydrogen-containing fuel gas turbine power generation system adapted by multi-modal data fusion according to an exemplary embodiment. DETAILED DESCRIPTION

[0051] The exemplary embodiments will be described in detail herein with reference to the attached drawings. When the description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the present application. Instead, they are merely examples of apparatuses and methods consistent with some aspects of the present application as detailed in the appended claims.

[0052] Embodiment One

[0053] Please refer to Figure 1 , Figure 1 is a schematic diagram of a low specific speed centrifugal compressor of a hydrogen-containing fuel gas turbine power generation system adapted by multi-modal data fusion according to an exemplary embodiment, the compressor comprising:

[0054] The meridian flow channel assembly 03 is a fixed airflow passage frame forming a continuous flow channel for airflow to pass through; the impeller and blade assembly 02 is a rotating supercharging component, which is arranged inside the meridian flow channel assembly 03, coaxially assembled with the meridian flow channel assembly 03 and maintaining a preset gap therebetween, so as to supercharge the airflow flowing into the meridian flow channel assembly 03 by rotation; the adaptive processing casing assembly 01 is a flow field regulation component, which is arranged outside the meridian flow channel assembly 03, rigidly connected with the meridian flow channel assembly 03 and coaxially assembled, and the inside thereof is correspondingly arranged with the impeller and blade assembly 02 and maintains an adjustable gap, so as to regulate the airflow state in real time; the meridian flow channel assembly 03, the impeller and blade assembly 02 and the adaptive processing casing assembly 01 are coaxially arranged, and together form a closed supercharging flow field, so as to realize the adaptation to the hydrogen-containing fuel gas turbine power generation system.

[0055] Further, the meridian flow channel assembly 03 comprises:

[0056] The meridian flow channel assembly 03 comprises an inlet section, an impeller section, a diffuser section and an outlet section in sequence along the airflow direction, and each section forms a continuous diverging flow channel;

[0057] The inlet section is rigidly connected with the air inlet pipeline through a flange;

[0058] The impeller section is a cylindrical cavity, the inner wall of which maintains a preset initial gap with the blade tip of the impeller, and is connected with the inlet section through a smooth transition curved surface;

[0059] The diffuser section has a flow channel width greater than that of the inlet section, and the inner wall thereof is fixedly installed with diffuser blades, and the top of the blade maintains a regulation gap with the inner wall of the adaptive processing casing;

[0060] The outlet section is a diffusion type structure, which is smoothly connected with the end of the diffuser section, and the outlet is connected with the air inlet pipeline of the combustion chamber through a flange.

[0061] Further, the meridian flow channel assembly 03 further comprises:

[0062] The entire meridian flow channel has a preset curvature radius and a meridian surface inclination angle, and each section is coaxially arranged.

[0063] In specific implementation, the impeller and blade assembly 02 comprises:

[0064] The impeller is integrally formed by high-strength alloy milling, the hub is rigidly connected with the compressor main shaft through a key groove, and the main shaft is supported at both ends by a bearing seat;

[0065] The blade root is connected with the tenon groove of the impeller rim through a dovetail tenon, the blade has a preset sweep angle, and the top of the blade maintains a preset initial gap with the inner wall of the adaptive processing casing;

[0066] The impeller and the blade assembly 02 are located in the impeller section of the meridian flow channel as a whole.

[0067] In a specific implementation, the self-adaptive processing casing assembly 01 includes a casing body, which is a ring sleeve structure formed by precision casting of cast iron and is rigidly connected to the shell flange of the meridian flow channel through bolts.

[0068] A plurality of annular movable guide vanes are uniformly distributed on the inner wall of the casing inlet section, the roots are hinged to the casing body through micro shafts, the ends are connected to the micro hydraulic push rod ball hinge of the actuator through the connecting rod mechanism, and the annular movable guide vanes can rotate around the shafts within a preset angle range.

[0069] The radial adjustable gap mechanism is a ring slider structure embedded in the inner wall groove of the casing near the impeller blade tip, the inner side of the slider corresponds to the blade tip, the outer side is slidingly connected to the casing body through an elastic guide column, and the other end is rigidly connected to the output end of another micro hydraulic push rod, so that the blade tip gap can be adjusted.

[0070] A plurality of piezoelectric pressure sensors are uniformly embedded between the impeller outlet and the diffuser inlet of the casing inner wall, the sensor probe is flush with the inner wall of the flow channel, the signal line is led out through the threading hole of the casing body and is electrically connected to the external controller.

[0071] Two groups of micro hydraulic push rods are respectively used to drive the annular movable guide vanes and the radial adjustable gap mechanism, and are fixedly installed on the bracket on the outer wall of the casing, the bracket is welded to the casing, and the push rod control signal line is electrically connected to the controller.

[0072] In one embodiment, the structure of the centrifugal compressor is described in detail in combination with a specific application scenario to embody the practical application mode of adapting to the 60kW hydrogen-containing fuel gas turbine power generation system.

[0073] 1. Overall structure and assembly relationship

[0074] The centrifugal compressor of the embodiment includes three modules of the meridian flow channel assembly 03, the impeller and blade assembly 02, and the self-adaptive processing casing assembly 01, which are coaxially assembled (the coaxiality is ensured by precise tooling) to form a closed pressurized flow field.

[0075] The meridian flow channel assembly 03 serves as a fixed frame to accommodate the impeller and blade assembly 02 and guide the airflow.

[0076] The impeller and blade assembly 02 serves as a rotating core to realize airflow pressurization through high-speed rotation.

[0077] The adaptive processing casing assembly 01 surrounds the outside and controls the flow field stability in real time.

[0078] 2. Meridian flow channel assembly 03

[0079] Inlet section: made of stainless steel, precision casting, convergent structure, bolted connection with the gas turbine power generation system inlet pipeline through the flange with sealing gasket (flange diameter matches the inlet pipeline), to ensure that the airflow enters the flow channel without leakage.

[0080] Impeller section: cylindrical cavity (integrally cast with the inlet section), the inner wall is precisely ground and processed, maintaining an initial gap of 0.3mm with the impeller tip (adapted to the rotating requirements of the impeller), the inlet section and the impeller section are connected through a smooth curve with a radius of 50mm, avoiding impact loss when the airflow enters the impeller.

[0081] Diffuser section: the flow channel width gradually increases along the airflow direction (12mm at the inlet section, 25mm at the end of the diffuser section), the inner wall is welded with 8 diffuser blades (blade made of TC4 titanium alloy, angle 12°), the blade top and the adaptive processing casing inner wall have a reserved gap of 0.2mm, considering the airflow flow and control requirements.

[0082] Outlet section: diffuser cone structure, smoothly welded with the end of the diffuser section, the outlet flange is connected with the combustion chamber inlet pipeline, realizing stable delivery of the pressurized airflow to the combustion chamber.

[0083] The entire meridian flow channel has a curvature radius of 50mm, a meridian surface inclination angle of 8°, and each section is processed through numerical control to ensure coaxiality (error ≤0.05mm), adapting to a rotating speed range of 15000-30000r / min.

[0084] 3. Impeller and blade assembly 02

[0085] Impeller: made of Inconel718 high-strength alloy and integrally milled (high temperature resistant, fatigue resistant), the hub is rigidly connected with the 45CrNiMoVA material compressor shaft through a keyway (keyway fit precision H7 / h6), the both ends of the shaft are supported on the bearing seat through angular contact ball bearings (model 7010AC), the bearing seat is fixed on the support of the meridian flow channel shell, ensuring stable rotation of the impeller.

[0086] Blades: a total of 12, made of TC11 titanium alloy after forging and precise milling, the blade root is a dovetail tenon, connected with the mortise of the impeller rim (fitting gap 0.03mm), the blade angle is designed as 8°, determined through multi-objective optimization in specific implementation, the blade top maintains an initial gap of 0.3mm with the adaptive processing casing inner wall, meeting the fatigue strength requirements.

[0087] The impeller and blade assembly 02 is integrally installed in the impeller section of the meridian flow passage. When the blades rotate, they push the airflow to flow from the inlet section to the diffuser section, realizing the conversion of kinetic energy to pressure energy.

[0088] 4. Implementation of adaptive processing casing assembly 01

[0089] Casing body: made of HT300 cast iron precision casting, in the form of a ring sleeve structure, connected to the flange of the meridian flow passage shell by 8 M10 bolts (tightening torque 35 N•m), and the inner wall is plated with chromium to reduce airflow friction loss.

[0090] Annular movable guide vane: a total of 8 pieces (aluminum alloy material), evenly distributed on the inner wall of the casing inlet section, the root is hinged to the casing through a 4mm diameter stainless steel micro shaft (clearance 0.02mm), which can rotate around the shaft within a range of -5°~10°; the end of the guide vane is connected to the micro hydraulic push rod (model DG10-30) through a connecting rod mechanism, realizing precise angle control.

[0091] Radial adjustable gap mechanism: a ring-shaped slider (made of wear-resistant cast iron) is embedded in the inner wall groove of the casing near the impeller tip, the outer side of the slider is slidingly connected to the casing body through four elastic guide columns (spring steel material) (sliding accuracy 0.01mm), and is rigidly connected to the output end of another micro hydraulic push rod (pushing force 80N), which can realize adjustment within a range of ±0.05mm of the tip gap.

[0092] Pressure sensor: four piezoelectric pressure sensors (model DYTRAN 3055B) are evenly embedded in the inner wall of the casing (between the impeller outlet and the diffuser inlet), the sensor probe is flush with the inner wall of the flow passage (to avoid interfering with the airflow), the signal line is led out through the threading hole of the casing body, and is electrically connected to the external PLC controller (model S7-1200), with a signal transmission accuracy of ±0.5% FS.

[0093] Micro hydraulic push rod: two sets of push rods drive the guide vane and the radial gap mechanism respectively, and are fixed on the welded bracket on the outer wall of the casing. The push rod control signal line is connected to the PLC controller, with a response time ≤50ms, and can act in real time according to the pressure signal.

[0094] 5. Overall adaptation effect

[0095] The centrifugal compressor of this embodiment is assembled in a 60kW hydrogen-containing fuel gas turbine power generation system, and when it is running:

[0096] The impeller and blade assembly 02 rotates at high speed (rated speed 28000r / min) under the drive of the main shaft, sucking air from the inlet section and compressing it, and then sending it into the combustion chamber after being pressurized by the diffuser section, and mixing and burning with hydrogen gas;

[0097] The adaptive processing casing assembly 01 monitors the flow field pressure in real time through the pressure sensor (sampling frequency 1 kHz), when the pressure fluctuation is detected to exceed 100 Pa, the PLC controller drives the guide vane adjustment angle (such as from 0° to 5°) or fine-tunes the tip clearance (such as from 0.3 mm to 0.25 mm), suppresses the airflow separation and leakage, and ensures stable operation;

[0098] The actual test shows that the air flow of the compressor is 750 g / s, the pressure ratio is 3.8, the efficiency is 85%, and the pressure fluctuation is 95 Pa under the rated working condition, which meets the high-efficiency and stable operation requirements of the 60 kW hydrogen-containing fuel gas turbine power generation system.

[0099] Through the above embodiment, the gradual expansion of the meridian flow channel assembly 03, the high-strength connection of the impeller and blade assembly 02, and the real-time regulation function of the adaptive processing casing assembly 01 form a synergistic effect, fully embodying the design goal of "low specific speed and high stability" of the present application, which can effectively adapt to the working condition requirements of the hydrogen-containing fuel gas turbine power generation system.

[0100] Specifically, the compressor is adapted to the hydrogen-containing fuel gas turbine power generation system, adopts a low specific speed design, and realizes high load and high stability through the following structural optimization:

[0101] 1. Meridian layout and blade modeling: In view of the loss problem caused by the high tip clearance ratio of the small flow compressor, an advanced meridian layout is adopted, the blade sweep angle and the diffuser blade angle are optimized, the high-efficiency flow characteristics in the whole speed range are considered, and the tip leakage loss, secondary flow loss and boundary layer loss are reduced.

[0102] 2. Adaptive processing casing: In view of the instability problem caused by the asymmetric flow channel of the volute and the flow distortion of the inlet and outlet, an adaptive processing casing is designed, and the stability control is realized by real-time regulation of the casing structure parameters.

[0103] Please refer to Figure 2 , Figure 2 is a flow chart of an optimization method of a low specific speed centrifugal compressor of an adaptive hydrogen-containing fuel gas turbine power generation system according to a multi-modal data fusion example embodiment, the method comprises:

[0104] S1. Real-time monitoring of the operating parameters of the compressor in the hydrogen-containing fuel gas turbine power generation system; the operating parameters include but are not limited to the flow, pressure ratio, efficiency, temperature, pressure fluctuation, power demand operating parameters of the power generation system monitored by multiple points at different parts of the compressor;

[0105] S2. Using a sensor fusion algorithm, the flow rate, pressure ratio, efficiency, temperature, pressure fluctuation, and power demand of the power generation system are monitored at multiple points in different parts of the compressor using a preset distributed sensor network, and the fused operating parameters are obtained;

[0106] S3. Using a fuzzy logic algorithm, the fused operating parameters are compared with the preset standard parameter range, and when the standard parameter range is exceeded, the optimization process is started.

[0107] The fuzzy logic algorithm is used to compare the fused operating parameters with the preset standard parameter range, and when the standard parameter range is exceeded, the optimization process is started, including:

[0108] Taking the pressure fluctuation in the fused operating parameters as the core representation parameter, the fuzzy logic algorithm is used to compare it with the preset stability standard parameter range, and when the pressure fluctuation exceeds the first range, it is determined that the compressor has a stability problem, triggering the preset first rule set;

[0109] Taking the efficiency and flow rate in the fused operating parameters as joint representation parameters, the fuzzy logic algorithm is used to compare them with the preset efficiency standard parameter surface, and when the actual operating point deviates from the standard surface by more than a first threshold value for a continuous preset number of sampling periods, the second rule set is triggered;

[0110] Taking the power demand of the power generation system and the actual output power of the compressor in the fused operating parameters as core parameters, a three-dimensional adaptability evaluation space is constructed by combining the efficiency and the preset surge margin, and the Euclidean distance from the current operating point to the standard adaptability surface is calculated by the fuzzy logic algorithm;

[0111] When the Euclidean distance exceeds a preset second threshold value, the third rule set is triggered.

[0112] In specific implementation, as described in the above steps, the optimization method of the present application mainly includes the following key steps:

[0113] 1. Data acquisition and fusion analysis

[0114] A distributed sensor network is used to monitor multiple points in different parts of the compressor, and real-time operating parameters such as flow rate, pressure ratio, efficiency, temperature, and pressure fluctuation are obtained.

[0115] A sensor fusion algorithm is used to fuse the collected multi-source data, obtaining accurate and comprehensive operating data. The fuzzy logic algorithm is used to compare the fused operating parameters with the preset standard parameter range, and when the standard parameter range is exceeded, the optimization process is triggered.

[0116] 2. Optimization strategies for different problems

[0117] Stability Optimization: A model predictive control algorithm is employed to control an adaptive adjustment device that adjusts the angle or cross-sectional area of the guide vanes of the non-axisymmetric flow passage and the inlet and outlet ports. According to the real-time pressure fluctuations, the model predictive control algorithm can predict the trend of flow changes in the flow passage, thereby automatically adjusting the device parameters to reduce the impact of flow distortion on the stability of the compressor. At the same time, an active control technology based on neural networks is introduced. According to the real-time monitoring of the pressure fluctuation signal, the learning and prediction ability of the neural network is used to automatically adjust the control parameters of active vortex control or active airflow injection, further enhancing the stability of the compressor under unstable conditions.

[0118] Efficiency Optimization: In small flow conditions, a genetic algorithm is used in combination with an intelligent control system. The flow change is used as input, and the reduction of tip leakage loss, secondary flow loss, and boundary layer loss is used as target to dynamically adjust the tip clearance size. At the same time, a surface roughness optimization algorithm is used to treat the blade surface of the compressor with a special coating with low friction coefficient and good wear resistance, effectively reducing the boundary layer loss.

[0119] Adaptability Optimization: Based on the power demand of the power generation system, a multi-objective particle swarm optimization algorithm is used to dynamically optimize the key design parameters of the compressor, such as blade shape, diffuser structure, and volute size. The algorithm considers multiple objectives such as efficiency, stability, and power matching to find the optimal combination of design parameters. An adjustable compressor structure based on adaptive control algorithm is developed, such as a variable geometry diffuser or a retractable volute, which can be adjusted adaptively to make the compressor better adapt to different power demand of the power generation system.

[0120] 3. Simulation verification and parameter adjustment

[0121] The optimized compressor model is simulated and analyzed using computational fluid dynamics (CFD) software, and a data-driven uncertainty quantification algorithm is used to evaluate the uncertainty of the simulation results.

[0122] A reinforcement learning algorithm is used to automatically adjust the optimization parameters based on the simulation results and uncertainty evaluation. If the expected optimization target is not achieved, the simulation and adjustment process is repeated until the expected effect is achieved.

[0123] 4. Establishing a performance database and knowledge mining A compressor performance database is established, and a knowledge graph algorithm is used to associate and analyze the operating parameters and optimization strategies before and after each optimization, to mine potential optimization directions and rules, and to provide reference for subsequent optimization. DETAILED EMBODIMENT

[0125] The optimization method of the present application is described in detail below in conjunction with specific embodiments.

[0126] EMBODIMENT

[0127] In a 60kW level hydrogen-containing fuel gas turbine power generation system, the optimization method of the application is applied to optimize the low specific speed centrifugal compressor.

[0128] Data acquisition and fusion analysis

[0129] Distributed sensors are arranged at key positions such as the inlet and outlet of the compressor and the blade surface to monitor operating parameters such as flow rate, pressure ratio, efficiency, temperature, and pressure fluctuation in real time. Data is collected every second, and multi-source data is fused by a sensor fusion algorithm to obtain accurate operating data. Fuzzy logic algorithm is used to compare and analyze the fused operating data with the preset standard parameter range. For example, when the pressure fluctuation exceeds the normal range of ±5%, the optimization process is triggered.

[0130] Optimization strategies for different problems

[0131] Stability optimization

[0132] A model predictive control algorithm is used to control the adaptive adjustment device. The device is installed at the non-axisymmetric flow channel and the inlet and outlet, and includes adjustable guide vanes and variable cross-sectional area flow channels. Based on the real-time monitoring of pressure fluctuation, the model predictive control algorithm predicts the future trend of flow changes in the flow channel for a certain period of time, and adjusts the angle of the guide vane and the cross-sectional area of the flow channel in advance to reduce flow distortion. At the same time, based on the neural network active control technology, the pressure fluctuation signal is monitored in real time, and through the learning and prediction ability of the neural network, the vortex intensity of the active vortex control device and the injection direction and flow of the active airflow injection device are automatically adjusted to enhance the stability of the compressor under unstable conditions.

[0133] Efficiency optimization

[0134] In the small flow condition (flow rate less than 30% of the rated flow rate), the genetic algorithm is started in combination with the intelligent control system. The flow rate change is used as the input, and the reduction of tip leakage loss, secondary flow loss, and boundary layer loss is used as the target to dynamically adjust the tip clearance size. At the same time, the blade surface of the compressor is treated with a special coating, which uses nanomaterials and has low friction coefficient and good wear resistance. Through the surface roughness optimization algorithm, the uniformity and roughness of the coating are ensured to meet the design requirements, effectively reducing the boundary layer loss.

[0135] Adaptability optimization

[0136] Based on the power demand of the power generation system, a multi-objective particle swarm optimization algorithm is used to dynamically optimize the key design parameters of the compressor, such as the shape of the blades, the structure of the diffuser, and the size of the volute. During the optimization process, multiple objectives such as efficiency, stability, and power matching are considered. For example, when the power demand of the power generation system decreases to 40kW, the multi-objective particle swarm optimization algorithm adjusts the bending angle of the blades and the expansion angle of the diffuser to improve the efficiency and stability of the compressor under low-power working conditions. At the same time, an adjustable compressor structure based on an adaptive control algorithm is developed, such as a variable-geometry diffuser and a telescopic volute. When the power demand of the power generation system changes, the adaptive control algorithm automatically adjusts the geometry of the diffuser and the telescopic length of the volute, enabling the compressor to better adapt to different power demands.

[0137] Simulation verification and parameter adjustment

[0138] CFD software such as ANSYS Fluent is used to simulate and analyze the optimized compressor model. During the simulation process, the influence of the asymmetric flow channel of the volute and the flow distortion of the inlet and outlet is considered, and the internal flow field distribution, pressure change, and airflow separation of the compressor under different working conditions are comprehensively analyzed. Data-driven uncertainty quantification algorithms are used to evaluate the uncertainty of the simulation results, such as calculating the confidence interval of the simulation results through the Monte Carlo simulation method. Reinforcement learning algorithms are used to automatically adjust the optimization parameters based on the simulation results and uncertainty evaluation. If the simulation results show that the efficiency of the compressor does not meet the expected target, the parameters such as blade shape and tip clearance are fine-tuned, and the simulation is performed again until the performance of the compressor is significantly improved.

[0139] Establishment of performance database and knowledge mining

[0140] A compressor performance database is established to record the operating parameters, optimization strategies, and simulation results before and after each optimization. Knowledge graph algorithms are used to associate and analyze the data in the database to mine potential optimization directions and rules. For example, through knowledge graph analysis, it is found that adjusting the blade sweep angle can significantly improve the efficiency of the compressor under certain specific flow and pressure working conditions. These knowledge provides an important reference for subsequent optimization.

[0141] In one embodiment, the present application has the following beneficial effects:

[0142] Significantly improve the stability of the compressor operation, and adapt to the high requirement device of hydrogen-containing fuel Through the adaptive processing of the annular movable guide vane of the casing assembly, the radial adjustable gap mechanism and the piezoelectric pressure sensor, the real-time regulation and control of the asymmetric flow channel, the inlet and outlet flow distortion are realized; In the optimization method, the pressure fluctuation is taken as the core characteristic parameter, combined with fuzzy logic judgment and the first rule set (model predictive control + neural network active control), the airflow separation caused by pressure fluctuation can be quickly suppressed, effectively solving the problem of insufficient stability of existing compressors caused by fast combustion speed and high flame temperature of hydrogen-containing fuel, improving the pressure fluctuation control precision of the compressor under wide operating conditions, and significantly improving the stability margin.

[0143] Optimize the efficiency of the whole operating condition, and consider the performance of small flow condition The high-strength alloy integral milling of impeller and blade assembly, the design of blade angle, and the gradually expanding structure of meridian flow channel reduce the basic flow loss; The optimization method reduces the tip leakage, secondary flow and boundary layer loss under small flow condition through the joint representation of efficiency and flow and the second rule set (genetic algorithm dynamically adjusts the tip clearance + surface optimization), solves the pain point that the traditional compressor cannot balance the efficiency and stability margin, and improves the efficiency of the whole operating condition, especially under small flow condition.

[0144] Enhance the adaptability of multiple operating conditions, and match the power demand of hydrogen-containing power generation system The adjustable structure (guide vane angle, radial gap) of the adaptive processing casing and the coaxial design of the meridian flow channel provide a hardware basis for wide operating condition adaptation; The optimization method realizes the accurate matching of the compressor to the variable power demand of the hydrogen-containing fuel gas turbine power generation system (such as 60kW level) through the three-dimensional adaptability evaluation space (power demand - efficiency - surge margin) and the third rule set (multi-objective optimization + reinforcement learning), solves the problem of immature multi-condition stability expansion and efficiency improvement technology of low specific speed compressors, and significantly improves the power response speed and adaptation accuracy.

[0145] Build an intelligent closed-loop optimization system to improve system reliability and economy The device and method are coordinated, multi-parameter accurate monitoring is realized through sensor fusion algorithm, fuzzy logic judgment, CFD simulation verification and knowledge graph mining are combined to form a closed-loop mechanism of "monitoring - judgment - regulation - feedback". This system can automatically adapt to the complex operating conditions of hydrogen-containing fuel gas turbine power generation system, reduce manual intervention and maintenance cost, and through continuous optimization iteration, ensure the long-term efficient and stable operation of the compressor, and provide core technical support for the large-scale application of hydrogen-containing fuel power generation system.

[0146] It can be understood that the same or similar parts in the above embodiments can be mutually referred to, and the contents not described in detail in some embodiments can be referred to the same or similar contents in other embodiments.

[0147] It should be noted that, in the description of the present application, the terms "first", "second" and the like are used only for descriptive purposes, and cannot be construed as indicating or implying relative importance. In addition, in the description of the present application, the meaning of "a plurality of" is at least two, unless otherwise specified.

[0148] Any process or method descriptions or descriptions of the flow diagrams described herein or otherwise described in the present application can be understood as representing code modules, segments, or portions of code that include one or more executable instructions for implementing specific logic functions (or steps) in the process, and that the various embodiments of the present application include additional implementations in which the order of the steps can be different, including use of the same step in different orders, use of different steps, or combination of the steps, all of which have been contemplated to be within the scope of the present application.

[0149] It should be understood that each part of the present application can be implemented in hardware, software, firmware or a combination thereof. In the above embodiments, a plurality of steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented in hardware, and as in another embodiment, it can be implemented by any one or a combination of the following technologies known in the art: discrete logic circuit with logic gate circuit for implementing logic function on data signal, application specific integrated circuit with suitable combination logic gate circuit, programmable gate array (PGA), field programmable gate array (FPGA) and the like.

[0150] Those skilled in the art of the present technology can understand that all or part of the steps carried out by the above-mentioned embodiment method can be completed by program instructions to the relevant hardware, and the program can be stored in a computer readable storage medium, which includes one or a combination of the steps of the method embodiment when executed.

[0151] In addition, each functional unit in each embodiment of the present application can be integrated in one processing module, or each unit can be physically present separately, or two or more units can be integrated in one module. The above integrated module can be realized in the form of hardware or in the form of software functional module. The integrated module, if realized in the form of software functional module and sold or used as an independent product, can also be stored in a computer readable storage medium.

[0152] The storage medium mentioned above can be a read-only memory, a magnetic disk or an optical disk, etc.

[0153] In the description of the specification, the description of the terms "one embodiment", "some embodiments", "an example", "a specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present application. In the specification, the illustrative description of the above terms does not necessarily mean the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.

[0154] Although the embodiments of the present application have been shown and described above, it is understood that the above-described embodiments are exemplary, and cannot be construed as limiting the present application, and those skilled in the art can make changes, modifications, replacements and variations to the above-described embodiments within the scope of the present application.

Claims

1. A low specific speed centrifugal compressor adapted for use in a hydrogen containing fuel gas turbine power generation system, characterized by, include: Meridian flow channel assembly is a fixed airflow channel frame that forms a continuous flow channel for airflow. The impeller and blade assembly is a rotary pressurizing component, which is integrally disposed inside the meridional channel assembly. It is coaxially assembled with the meridional channel assembly and a preset gap is maintained between them, so as to pressurize the airflow flowing into the meridional channel assembly through rotation. The adaptive processing casing assembly is a flow field control component. It is arranged around the outside of the meridional flow channel assembly, rigidly connected to the meridional flow channel assembly and coaxially assembled. Its inner side is correspondingly arranged with the impeller and blade assembly and maintains an adjustable gap to control the airflow state in real time. The meridional flow channel assembly, impeller and blade assembly, and adaptive processing casing assembly are coaxially arranged to form a closed pressurized flow field, enabling adaptation to hydrogen fuel gas turbine power generation systems. The meridional flow channel assembly includes: The meridional flow channel assembly includes, in sequence along the airflow direction, an inlet section, an impeller section, a diffuser section, and an outlet section, with each section forming a continuous, gradually expanding flow channel; The inlet section is rigidly connected to the intake pipe via a flange. The impeller section is a cylindrical cavity, with its inner wall maintaining a preset initial gap with the impeller blade tip, and connected to the inlet section through a smoothly transitioning curved surface; The diffuser section has a wider flow channel than the inlet section, and diffuser blades are fixedly installed on the inner wall. An adjustment gap is reserved between the top of the blades and the inner wall of the adaptive processing casing. The outlet section has a diffuser structure and is smoothly connected to the end of the diffuser section. The outlet is connected to the combustion chamber intake pipe via a flange. The adaptive handling casing assembly includes: The casing body is made of precision cast iron and has an annular sleeve structure. It is rigidly connected to the outer flange of the meridional channel by bolts. Multiple annular movable guide vanes are evenly distributed on the inner wall of the inlet section of the casing. The root is hinged to the casing body through a miniature rotating shaft, which can rotate around the rotating shaft within a preset angle range. The end is connected to the miniature hydraulic push rod ball joint of the actuator through a linkage mechanism. The radially adjustable clearance mechanism is a ring-shaped slider structure, which is embedded in the groove of the inner wall of the casing near the tip of the impeller. The inner side of the slider corresponds to the tip of the impeller, and the outer side is slidably connected to the casing body through an elastic guide post. It is also rigidly connected to the output end of another set of miniature hydraulic push rods, which can realize the adjustment of the tip clearance. Multiple piezoelectric pressure sensors are evenly embedded between the impeller outlet and the diffuser inlet on the inner wall of the casing. The sensor probes are flush with the inner wall of the flow channel, and the signal lines are led out through the wiring holes in the casing body and electrically connected to the external controller. Two sets of miniature hydraulic push rods drive the annular movable guide vane and the radially adjustable clearance mechanism respectively. They are fixedly installed on the bracket on the outer wall of the casing. The bracket is welded to the casing. The push rod control signal line is electrically connected to the controller. The meridional flow channel assembly, impeller and blade assembly, and adaptive processing casing assembly are coaxially arranged to form a closed pressurized flow field, enabling adaptation to hydrogen fuel gas turbine power generation systems.

2. A low specific speed centrifugal compressor adapted for use in a hydrogen containing fuel gas turbine power system according to claim 1, characterized in that The meridional flow channel assembly further includes: The entire meridional channel has a preset radius of curvature and meridional plane tilt angle, and each section is set coaxially.

3. A low specific speed centrifugal compressor adapted for use in a hydrogen containing fuel gas turbine power system according to claim 1, characterized in that, The impeller and blade assembly includes: The impeller is integrally formed by milling with high-strength alloy, the hub is rigidly connected with the compressor main shaft through a key groove, and the main shaft is supported at both ends by bearing seats; The blade root is connected with the mortise groove of the impeller rim through a dovetail tenon, the blade has a preset sweep angle, and the blade top maintains a preset initial gap with the inner wall of the self-adaptive treatment casing; The impeller and the blade assembly are located in the impeller section of the meridian flow passage.

4. A method for optimizing a low specific speed centrifugal compressor adapted to a hydrogen-containing fuel gas turbine power generation system, applied to the low specific speed centrifugal compressor adapted to a hydrogen-containing fuel gas turbine power generation system according to any one of claims 1 to 3, characterized in that, The method comprises: Real-time monitoring of the operating parameters of the compressor in the hydrogen-containing fuel gas turbine power generation system; the operating parameters include but are not limited to the flow rate, pressure ratio, efficiency, temperature, pressure fluctuation, and power demand operating parameter of the power generation system at different positions of the compressor; Using a sensor fusion algorithm, the flow rate, pressure ratio, efficiency, temperature, pressure fluctuation, and power demand operating parameter of the power generation system at different positions of the compressor are fused by using a preset distributed sensor network to obtain fused operating parameters; Using a fuzzy logic algorithm, the fused operating parameters are compared with the preset standard parameter range, and when the standard parameter range is exceeded, an optimization process is started.

5. The method of claim 4, wherein, The fuzzy logic algorithm is used to compare the fused operating parameters with the preset standard parameter range, and when the standard parameter range is exceeded, the optimization process is started, which comprises: Taking the pressure fluctuation in the fused operating parameters as the core characteristic parameter, the fuzzy logic algorithm is used to compare it with the preset stability standard parameter range, and when the pressure fluctuation exceeds the preset first range, it is determined that the compressor has a stability problem, triggering the preset first rule set; Taking the efficiency and flow rate in the fused operating parameters as the joint characteristic parameters, the fuzzy logic algorithm is used to compare them with the preset efficiency standard parameter surface, and when the actual operating point deviates from the standard surface by more than a first threshold value for a continuous preset number of sampling periods, the second rule set is triggered; Taking the power demand of the power generation system and the actual output power of the compressor in the fused operating parameters as the core parameters, a three-dimensional adaptability evaluation space is constructed by combining the efficiency and the preset surge margin, and the Euclidean distance from the current operating point to the standard adaptability surface is calculated by the fuzzy logic algorithm; When the Euclidean distance exceeds a preset second threshold value, the third rule set is triggered.

6. The method of claim 5, wherein, The fuzzy logic algorithm is used to compare the fused operating parameters with the preset standard parameter range, and when the standard parameter range is exceeded, the optimization process is started, which comprises: Taking the efficiency and flow rate in the fused operating parameters as the joint characteristic parameters, the fuzzy logic algorithm is used to compare them with the preset efficiency standard parameter surface, and when the pressure fluctuation exceeds the preset first range, a model predictive control algorithm is used to control the self-adaptive treatment casing assembly, the flow change trend in the flow passage is predicted according to the real-time pressure fluctuation, and the guide vane angle or cross-sectional area of the non-axisymmetric flow passage and the inlet and outlet is automatically adjusted. The neural network-based active control technology is introduced, and the control parameters of active vortex control or active airflow injection are automatically adjusted according to the real-time monitored pressure fluctuation signals and the learning and prediction ability of the neural network.

7. The method of claim 5, wherein, The efficiency and flow rate in the fused operating parameters are taken as the joint representation parameters, which are compared with the preset efficiency standard parameter surface through a fuzzy logic algorithm, when the actual operating point deviates from the standard surface by more than a first threshold value for a continuous preset number of sampling periods, a second rule set is triggered, including: The efficiency and flow rate in the fused operating parameters are taken as the joint representation parameters, which are compared with the preset efficiency standard parameter surface through a fuzzy logic algorithm, when the actual operating point deviates from the standard surface by more than a first threshold value for a continuous preset number of sampling periods, a genetic algorithm is used to dynamically adjust the tip clearance size by taking the flow rate change as the input and taking the reduction of tip leakage loss, secondary flow loss and boundary layer loss as the target.

8. The method of claim 5, wherein, The optimization process further includes: The optimized compressor model is simulated and analyzed by using computational fluid dynamics software, and the uncertainty of the simulation results is evaluated by using a data-driven uncertainty quantification algorithm; A reinforcement learning algorithm is used to automatically adjust the optimization parameters according to the simulation results and uncertainty evaluation, and if the expected optimization target is not reached, the simulation and adjustment process is repeated until the expected effect is achieved; At the same time, a compressor performance database is established, and a knowledge graph algorithm is used to associate and analyze the operating parameters and optimization strategies before and after each optimization, to mine potential optimization directions and rules, and to provide a reference for subsequent optimization.

Images