342 results about "Compressor blade" patented technology

The invention discloses a gas compressor blade mean camber line design method, a gas compressor blade, a gas compressor and an aero-engine, and the method comprises the steps: S1, obtaining known design data, including an inlet blade angle theta in, an outlet blade angle theta out, a mean camber line starting point coordinate, a mean camber line end point abscissa, and turning angles delta theta 1, delta theta 2 and delta theta 4 of a first section arc, a second section arc and a fourth section arc, and abscissas of all tangency points; and S2, each section of arc is calculated through a geometric analysis method, a mean camber line is constructed after circle center coordinates, arc radiuses and tangent point coordinates of each section of arc are calculated, and the mean camber line is formed by sequentially and tangentially connecting four sections of arcs according to the sequence of convex, concave, convex and concave. The gas compressor blade mean camber line design method is good in adaptability and multiple in controllable point in the high Mach number state; therefore, the requirements of an advanced compressor are met; design parameters are greatly reduced, the optimizing period is greatly shortened, the adjusting efficiency is high, and the time is short.

The invention provides a gas compressor moving blade tip clearance measuring method and device, and belongs to the field of aero-gas turbine gas compressors. The problems of low measurement precision, low measurement efficiency and small measurement range in the prior art are solved. The method comprises the following steps that an angle encoder is installed on a main shaft, and a three-dimensional laser profile measuring instrument is arranged on the blade tip side of a blade at intervals; the impeller is rotated, the three-dimensional laser profile measuring instrument scans the blade tip, and three-dimensional point cloud data of the whole circle of blade tip profile are obtained; after the casing and the impeller are assembled, a plurality of continuous blades on the impeller are detached, and the three-dimensional laser profile measuring instrument is arranged at the vacant position of the impeller; the impeller is rotated, the three-dimensional laser profile measuring instrument scans the inner wall of the casing, and three-dimensional point cloud data of the whole circle of the inner wall of the casing are obtained; processing data; registering the processed three-dimensional point cloud data of the blade tip contour and the processed three-dimensional point cloud data of the inner wall in the same coordinate system to form a registration model; and the blade tip clearance value of the whole circle is calculated. The method is mainly used for measuring the blade tip clearance.

The invention belongs to the technical field of aircraft engine compressor blade detection, and discloses an aircraft engine compressor blade erosion damage prediction method and system based on a PINN. The method comprises the following steps: constructing an erosion damage rate equation and a flow field-particulate matter coupling equation aiming at the erosion damage judgment of the blade of the gas compressor; performing dual-drive loss function design, constructing a physical information neural network (PINN) model, and performing adaptive training on the constructed physical information neural network (PINN) model; the invention relates to gas compressor blade erosion damage prediction and engineering application. According to the method, the limitation of the prior art is overcome, a more accurate and reliable damage prediction model is provided, and powerful support is provided for design, operation and maintenance and safety evaluation of the aero-engine. According to the innovative method, the physical law and the data driving technology can be combined, and the damage prediction precision and efficiency of the aero-engine compressor blade under the complex working condition are improved.

The invention discloses a turbofan engine compressor blade crack multi-modal monitoring system, and belongs to the field of multi-modal monitoring, and the system comprises a multi-modal acquisition module which obtains the multi-modal data of each compressor blade, carries out the dynamic filtering denoising and temperature compensation preprocessing, completes the time axis alignment, and carries out the data reconstruction and feature extraction; and constructing a multi-modal feature vector. And the triggering module carries out preliminary abnormality diagnosis according to the judgment result, judges whether the blade is abnormal or not through a key feature threshold, determines whether to trigger depth evaluation or not by combining a periodic threshold, identifies a potential crack blade and generates an excitation decision. And when an excitation decision is executed, the intelligent diagnosis module monitors the strain gradient change to perform excitation monitoring, compares the vibration characteristics of a potential crack blade with the vibration characteristics of a contrast blade, judges whether a crack exists or not, and realizes multi-stage early warning, so as to solve the problem that the crack of the turbofan engine compressor blade is difficult to quickly detect in real time in the prior art. And safe and stable operation of the engine is guaranteed.

The invention relates to the technical field of aviation turboshaft engines, and provides a method for evaluating the influence of sand dust erosive wear on the performance of a turboshaft engine, which comprises the following steps: calculating the amount of sand dust sucked into the turboshaft engine; calculating and solving an air flow field in the air compressor channel and a movement track of sand dust particles by adopting computational fluid mechanics software; establishing a mathematical model of erosive wear of the air compressor blade of the turboshaft engine caused by sand dust; on the basis of the motion trail and the mathematical model, the blade profile of the blade after abrasion is obtained, the airflow field in the air compressor channel after abrasion is further calculated and solved, and the reduction amount of the efficiency of the air compressor after sand dust erosion abrasion is obtained; and on the basis of the reduction amount of the compressor efficiency, engine overall performance calculation software is adopted to calculate and evaluate the engine performance parameter change condition. According to the method, a mathematical model of compressor blade abrasion is constructed, the turbine shaft engine performance degradation evaluation method is provided, and quantitative analysis and evaluation of turbine shaft engine performance degradation in the sand and dust environment are achieved.

The invention provides a gas compressor blisk rupture rotation speed prediction method based on virtual-real fusion, belongs to the technical field of aero-engines, and particularly relates to an aero-engine gas compressor blisk rupture rotation speed prediction method by establishing a rupture rotation speed-oriented aero-engine gas compressor blisk digital twin model and performing double correction on the model and a failure criterion by using test real-time data. And in the simulation process, a parallel computing technology is used for acceleration, so that a high-precision fracture rotation speed prediction value which aims at a single individual of the aeroengine compressor blisk and accords with physical rules and actual test measurement can be quickly obtained.

The invention discloses a high-load supersonic compressor blade profile design method coupled with multi-point plasma excitation, which comprises the following steps: generating high-load large-bend blade profile geometric data on the basis of original geometric data by using a blade profile parameterization modeling method; the method comprises the following steps: acquiring compressor blade channel flow field characteristics under a low Reynolds number working condition through numerical simulation, and determining a blade surface flow separation area under the low Reynolds number; determining a multi-point rapid heating plasma excitation layout mode according to the characteristics of the flow separation area; and analyzing the flow control effect of the multi-point rapid heating plasma excitation on the blade type shock wave / boundary layer interference of the supersonic gas compressor. According to the method, the K-H instability of a shear layer is triggered by applying multi-point rapid heating plasma excitation in a flow field, a spanwise vortex array structure is induced to be formed, small-scale vortexes in a flow separation area are promoted to be mixed and evolved into a spanwise large vortex structure so as to accelerate dissipation, and the effect of inhibiting flow separation is achieved.

The invention discloses a gas compressor blade state monitoring method and system based on a health management platform, and relates to the technical field of gas turbines. Comprising the following steps: acquiring real-time operating parameters of the gas turbine, and transmitting the real-time operating parameters to a health management platform at a fixed sampling frequency; performing data preprocessing and feature extraction on the real-time operation parameter data; calculating the performance parameter degradation quantity of the gas turbine according to the real-time operation parameter data; performing blade fault identification according to the parameter degradation quantity and a preset fault diagnosis criterion; calculating a fault early warning index through the real-time operation parameter data, and judging whether the gas turbine is in a normal operation condition or not; and judging a fault early warning level according to the parameter degradation quantity and sending out a corresponding early warning signal. According to the method, the blade fault type can be accurately predicted, false alarms and false alarms can be reduced, meanwhile, early warning level signals are sent out, measures can be taken, fault expansion is avoided, and downtime and maintenance cost are reduced.

The invention provides a communication and interaction method of a digital twinning system in a compressor blisk machining process, and relates to the technical field of digital twinning and aeronautical manufacturing, and the method comprises the steps: collecting vibration, temperature and acoustic emission data in the compressor blisk machining process in real time, analyzing machine tool machining data, carrying out the alignment and noise reduction of the collected data, and obtaining a digital twinning result; then time-frequency domain mixed feature extraction is carried out, and time-frequency domain mixed feature data are optimized and uploaded in a graded mode; a deterministic transmission network is constructed, data transmission priorities of 5G communication and LoRa dual channels are dynamically adjusted according to a network load, and intelligent switching between 5G communication and a LoRa protocol is realized based on a switching decision model; analyzing normal processing data of the whole stage of the processing process, and establishing a processing data thread; and predicting the abnormal processing risk in the processing process, and updating the model parameters. According to the method, the communication and interaction efficiency of the digital twin system in the machining process of the compressor blisk in the aero-engine can be improved.

The invention belongs to the field of aero-engines and turbines, and provides a quick prediction method, system and device for a two-dimensional viscous compressible flow field of a gas compressor and a medium, and the method comprises the steps: obtaining CFD simulation data of a two-dimensional blade profile of the gas compressor under multiple working conditions, and carrying out the preprocessing to obtain a standardized training data set; on the basis of the data set, constructing a hybrid neural network model which takes a blade profile geometric parameter and an operation condition parameter as input and takes a two-dimensional viscous compressible flow field as output; combining mean square error, gradient loss and physical consistency loss based on RANS equation residual error to construct a total loss function, and performing end-to-end training on the model; during reasoning, to-be-predicted parameters are input into the trained model according to the same preprocessing mode, and then a flow field prediction result can be rapidly output. According to the method, the problems of long consumed time, low precision and poor consistency of traditional CFD simulation can be solved, millisecond-level flow field prediction is achieved, high precision and high physical consistency are achieved, and the method is suitable for efficient optimization design of the blade profile of the gas compressor.

The invention discloses a gas compressor rotor blade surface defect detection device and a detection method thereof, and belongs to the technical field of gas compressor rotor blade detection. The gas compressor rotor blade surface defect detection device comprises a detection platform, an electric index plate clamping device, a tip cone stopping device and a flaw detection device, the electric index plate clamping device and the tip cone stopping device are matched to perform axial fixation and precise index driving on the two ends of the to-be-tested compressor rotor; the flaw detection device is used for detecting surface defects of the rotor blade of the gas compressor on the basis of an ultrasonic flaw detection principle; compared with existing artificial flaw detection of aero-engine compressor rotor blades, the method can accurately collect, process and analyze the surface defects of each stage of blade of the detected compressor rotor, can realize the positioning of each stage of blade and the traceability of the detection result, ensures the integrity of the measurement result, and improves the detection accuracy. The problem that the detection result is influenced by subjective factors in the existing artificial flaw detection of the aero-engine compressor rotor blade is solved.

The invention discloses a method for quickly generating a compressor blade profile containing local geometric deviation. The method comprises the following steps: determining a mean camber line point and thickness distribution according to geometric data of a suction surface and a pressure surface; determining parameterized expression of the mean camber line geometry according to the camber line points, and obtaining parameter expression of a thickness distribution curve according to the thickness distribution; generating pressure surface geometric points and suction surface geometric points containing local geometric deviation based on parameterized expression of mean camber line geometry and parameterized expression of the thickness distribution curve; a blade profile leading edge curve and a blade profile trailing edge curve are generated; and integrating the curve data to generate the blade profile containing the local geometric deviation. The blade obtained on the basis of the method contains the local geometric deviation, control over the machining deviation of the blade is facilitated, and the method has great significance in determining the influence of the typical geometric deviation of the blade on the aerodynamic characteristics of the gas compressor through simulation calculation.

The disclosure concerns a compressor blade for gas turbine engine. Specifically the blades of the compressor are modified according to predetermined requirements for both aerodynamic stability and fuel economy in multiple planes.

The invention belongs to the field of intelligent manufacturing of aero-engines, and provides a parametric modeling method for structural characteristics of typical parts of an aero-engine. According to the method, efficient precision machining of the aero-engine compressor blade is achieved through an intelligent system of parametric modeling, feature self-recognition and rapid programming. The specific implementation process comprises the steps that a three-dimensional model is generated through a parametric modeling module on the basis of a tenon structure parameter set and a blade body profile geometric feature parameter set input by a user; secondly, a feature recognition module is used for conducting multi-level machining feature decomposition on the three-dimensional model, and key machining features such as a tenon and a blade body profile are precisely recognized through a geometric topology analysis and depth feature learning fusion algorithm; on the basis, intelligent matching and optimization of the machining technology are achieved for the recognized machining features through a rapid programming module, the machining program is optimized through physical simulation, and finally the machining program applied to the production field is generated.

The invention provides a rotating speed determination method in aero-engine complete machine three-dimensional simulation, and belongs to the technical field of aero-engine simulation, and the method specifically comprises the steps: constructing a fluid-structure interaction control equation on each grid unit of an aero-engine complete machine geometric model; forming an integral coupling matrix, and solving the integral coupling matrix; simulating the calculated thermal state geometric model; the gas compressor and the turbine can only rotate around the rotating shaft; calculating aerodynamic forces acting on the compressor blades and the turbine blades; in each time step, the rotating speed is updated according to the angular acceleration; and after a plurality of iterations, when the difference value of the aerodynamic torque borne by the gas compressor and the aerodynamic torque borne by the turbine accords with a preset range, the corresponding rotating speed is the steady-state working rotating speed of the engine under the thermal state geometry. According to the processing scheme, the engine can automatically match and dynamically determine the working rotating speed in the simulation process, the inaccuracy of the preset rotating speed is avoided, and the precision and reliability of a simulation result are improved.

A turbine wheel may include an inner hub having a central axis, an outer ring concentric with the inner hub, and an intermediate ring concentrically disposed between the inner hub and the outer ring, and a plurality of turbine blades extending between the intermediate ring and the outer ring. The turbine blades may be oriented to be driven by a fluid stream flowing through the turbine wheel to rotate the turbine wheel in a first direction about the central axis. In addition, the turbine wheel may further include a plurality of compressor blades extending between the inner hub and the intermediate ring. Also, the compressor blades may be oriented to propel a fluid in a downstream direction when the turbine wheel is rotated in the first direction.

A multi-degree-of-freedom milling device for compressor blades, comprising a blade positioning clamping device, an automatic tool changing device and a multi-axis robot arm; the blade positioning clamping device comprises a blade tenon processing clamping and positioning mechanism and a blade surface processing clamping and positioning mechanism, which are used to fix the engine blades; the automatic tool changing device comprises an automatic tool changing tool magazine mechanism and an automatic tool changing execution end mechanism; the multi-axis robot arm comprises a first axis structure of a base, a second axis structure, a third axis structure of a small arm, a fourth axis small arm structure, a fifth axis wrist structure and a processing spindle structure. The present invention provides a multi-degree-of-freedom milling device for compressor blades, which utilizes a robot arm to realize flexible milling and automatic tool changing, can make machine tool processing more flexible, fast and accurate, positioning more accurately and faster, blade processing efficiency is high, and blade surface milling quality is high.

The invention relates to the technical field of fluid mechanics, in particular to an efficient simulation method and system for turbofan engine compressor blade sand dust erosion. The efficient simulation method for sand dust erosion of the blades of the turbofan engine compressor comprises the following steps of performing unsteady calculation on a full-stage and full-ring airflow field of the compressor until the airflow field converges, and extracting airflow field data of moving blade and stationary blade areas of each stage; according to the airflow field absolute speed data of each stage of moving blade area, obtaining airflow field relative speed data of each stage of moving blade area; setting the particle size, the initial flow, the initial position and the initial speed of sand dust at an inlet of the gas compressor; after entering the gas compressor, the sand dust sequentially passes through each stage of stationary blade and movable blade area in the gas compressor at a corresponding movement speed, and the absolute speed data and the relative speed data of the airflow field of each stage of movable blade and stationary blade area are combined to obtain the real-time movement track of the full-stage and full-ring sand dust in the gas compressor. Further obtaining the position, angle and speed of the impact point of the sand dust and the blade, and finally obtaining the erosion abrasion loss of the blade.

The invention discloses a compressor blade grinding model optimization method, which is characterized in that after a compressor blade theoretical model is split according to regions, compared with an integral theoretical model, the compressor blade theoretical model is more beneficial to programming and optimization of machining programs of each region according to numerical control grinding steps. A compressor blade theoretical model has the phenomena of local curvature radius sudden change, distortion, intersection and folding of molded surfaces at corners and the like, so that a cutter projection cannot be attached; each curved surface part of the optimized and reconstructed model is in smooth transition, and the tool path is uniform and smooth. The reference cutter shaft vector is given, cutter shaft control can be conveniently carried out during numerical control grinding machining programming, cutter shaft swing in program control is more consistent, the connecting positions of all machining programs are smoother, and the consistency of numerical control grinding machining surfaces is improved.

The invention belongs to the technical field of metal additive manufacturing, and particularly relates to a gas turbine compressor blade additive manufacturing device which comprises a machine body, and a workbench is arranged in the machine body; the bottom of the box body is rotationally connected with a rotating plate; the powder spreading mechanism is used for bidirectional powder spreading; the grinding mechanism is used for grinding sintered and accumulated powder in the blade material adding process; the powder scraping mechanism is used for removing powder attached to the grinding mechanism; and the powder collecting mechanism is used for collecting powder. The grinding mechanism can rotate along with work of the powder laying mechanism and grind sintered and accumulated powder in two directions, the roughness of a blade cooling channel is reduced in the additive manufacturing process, the communicating state of powder outlet plates on the two sides of a grinding roller can be switched through rotation of a rotating plate on the box body, the interlayer retention time of additive manufacturing is shortened, and the efficiency of additive manufacturing is improved. And therefore, the heat dissipation efficiency of the blade cooling channel after additive manufacturing is improved.

The invention discloses an axial flow compressor blade anti-erosion optimization method facing a sand and dust environment, and belongs to the technical field of compressor blade anti-erosion design and optimization. According to the method, on the basis of a gas-solid two-phase flow erosion mechanism in a sand and dust environment, links such as working condition analysis, parameterization platform building, constrained multi-objective optimization method design, model building and optimization and index verification are integrated, and an integrated anti-erosion optimization process is formed. CFturbo, AutoGrid, CFX and Matlab are called in a unified mode through a Python script, automatic coupling of geometric modeling, grid division, gas-solid coupling simulation and an intelligent optimization algorithm of the blade is achieved, and collaborative optimization of aerodynamic performance and erosion resistance can be achieved under the constraint of erosion wear. Compared with a traditional method which depends on experience modification or single simulation, the method has the advantages that the optimization efficiency is remarkably improved while the simulation precision is guaranteed, the personal error risk is reduced, and the method can flexibly adapt to different compressor models and diversified operation conditions.

The utility model discloses an on-line dynamic balance measuring system for a gas turbine rotor, and the system comprises a gas compressor housing which is internally provided with a gas compressor blade; one side of the combustion chamber shell is connected with the gas compressor shell, the gas compressor blades and the turbine power blades are arranged in the shell, the corresponding shell is detached according to the positions where the blades need to be replaced, the rotor is rotated to a proper angle through a turning mechanism of the gas turbine, and the blades are sequentially detached and replaced with new blades; the balancing weight mounting opening is formed in the side wall of the combustion chamber shell; the exhaust chamber is connected with the other side of the combustion chamber shell; the measuring system module adopts a man-machine interaction system of a gas turbine generator set, solves the problem that the residual unbalance amount of a rotor is out of tolerance after blades of a gas turbine are replaced, and reduces the processes of large decomposition of the gas turbine, disassembly of a housing, disassembly of related complete systems, long-distance transportation of the rotor, reassembly and the like.

The invention discloses a compressor blade with a venturi tube micro-channel cooling structure, which realizes uniform distribution of cooling air and forms a stable air film cooling layer on the surface of the blade by arranging arc-shaped fine channels and fine pores on the tip of the blade and combining the series design of adjacent channels, thereby obviously improving the cooling effect. The inner wall of the channel is of a sharkskin microcosmic placoid scale structure, friction resistance is reduced, the airflow turbulence characteristic is enhanced, and therefore the heat exchange performance is optimized. The grooves penetrating through the surface of the blade prolong the service life of the blade by changing the flowing path of the air flow and destroying the formation of a liquid film cooling layer, and enhance the cooling effect and the contact between the air flow and the surface of the blade through linkage with the small channels, thereby further improving the heat exchange performance. And the micropores of the damping boss not only provide a damping effect, but also can effectively release cooling air, so that the combination of cooling and structural stability is improved. While the cooling effect is optimized, the working efficiency of the blade is remarkably improved, and the service life of the blade is remarkably prolonged.

The invention provides a test device for simulating volcanic ash erosion sample materials at normal temperature. The test device comprises a gas supply system, a dust supply system, a gas-solid mixing system and an erosion test system, the gas supply system comprises an air compressor, a high-pressure gas storage tank and an air dryer which are connected in sequence, and an outlet of the air dryer is connected with the gas-solid mixing system; the dust supply system comprises a solid particle storage tank, the upper end of the solid particle storage tank is provided with a feed port, and a lower end outlet is connected with the gas-solid mixing system; the washout test system comprises a test chamber, a fixed disc which is arranged at an inlet of the test chamber and is communicated with the gas-solid mixing system, a nozzle on the fixed disc, and a sample disc which is positioned in the test chamber and is opposite to the fixed disc, and the nozzle is used for uniformly spraying solid particles onto a sample material on the sample disc. The test device can accurately simulate the erosive wear condition of the air compressor blade by the volcanic ash with different concentrations and speeds at normal temperature, and can also simulate the erosive damage condition of the air compressor blade and a thin-wall piece sample by the volcanic ash at a high rotating speed.

The invention aims to provide a compressor blade vibration fatigue failure probability evaluation method. The method comprises the following steps: constructing a probability Goodman curve of a blade material; obtaining the vibration stress distribution of the blade at the dangerous rotating speed; determining a vibration fatigue dangerous part of the blade, and obtaining the steady-state stress of the vibration fatigue dangerous part; and calculating the vibration fatigue failure probability of the dangerous part of the blade according to the steady-state stress and the vibration stress amplitude of the vibration fatigue dangerous part of the blade based on the blade material probability Goldman curve. The evaluation method can solve the problems that an existing blade vibration fatigue failure probability evaluation method does not conform to the design thought of high-cycle fatigue infinite life of the blade, the test amount is large, and engineering feasibility is lacked.

The invention provides a gas compressor blade root mounting structure, a gas compressor and a blade root mounting method.The mounting structure comprises a wheel disc, first groove bodies are formed in the wheel disc and distributed in the axial direction of the wheel disc, second groove bodies are distributed in the annular direction of the wheel disc, a locking structure comprises a first locking block and a second locking block, and the first locking block is provided with a first notch in the annular direction of the wheel disc; a protrusion is arranged on the side, close to the first locking block, of the second locking block, in the first state, the first notch is filled with the protrusion, the other side of the second locking block is flush with the side wall of the first groove body, and in the second state, the first end face of the protrusion makes contact with the second end face of the first locking block. The sum of the sizes of the first locking block and the second locking block in the annular direction of the wheel disc is larger than the size of the second groove body, the other side of the second locking block makes contact with the first blade, and axial movement of the first blade is limited. According to the mounting structure, by means of displacement of the second locking block, locking of the blades is achieved after the blades are mounted, and the integrity of the flow channel is guaranteed.

The invention provides an aero-engine blade anti-resonance polishing parameter determination method, and relates to the technical field of aero-engine compressor blade manufacturing, and the method comprises the steps: firstly testing the inherent frequency of a blade, determining an initial polishing parameter according to the surface quality requirement of the blade, testing the excitation frequency of a polishing system, and determining the polishing parameter; when the excitation frequency is equal to the first-order inherent frequency to the fifth-order inherent frequency, whether the corresponding stress value is larger than 200 MPa or not is judged; if the corresponding stress value is larger than 200 MPa, it is indicated that resonance occurs under the vibration frequency of the order, the initial polishing parameters are adjusted, the stress value corresponding to the excitation frequency of each order is tested again, and whether resonance occurs or not is judged; and if the corresponding stress value is smaller than 200 MPa, resonance does not occur under the vibration frequency of the order, and the polishing parameters are adopted for machining. And the step is repeated until the excitation frequency is equal to the first-order to fifth-order inherent frequency in the machining process, and when the stress value is smaller than a set threshold value, the set of parameters are polishing parameters.

The invention provides an additive repair blade high-cycle fatigue limit prediction method based on random defect probability distribution, and relates to the field of aero-engine fan and compressor blade maintenance, and the method comprises the steps: obtaining the defect distribution of a real blade; establishing a prediction model based on a critical distance theory; according to the prediction model, critical distances of the multiple real blades are determined, and a first critical distance is generated; performing defect reconstruction based on the defect distribution of the real blade to generate a virtual blade; obtaining the first high-cycle fatigue strength of the virtual blade according to the defect distribution of the virtual blade, the first critical distance and the prediction model; respectively determining a plurality of defect parameters and a Pearson coefficient of the first high-cycle fatigue strength, and screening a first parameter significantly related to the first high-cycle fatigue strength; constructing a fatigue strength evaluation model; and inputting the first parameter into the trained fatigue strength evaluation model, and outputting the predicted high-cycle fatigue strength. According to the scheme, the high-cycle fatigue limit of the blade can be quickly predicted, and the prediction accuracy is improved.

The invention discloses an optimization method of an aero-engine warm-up process, which comprises the following steps of: firstly, acquiring corresponding samples of a high-pressure turbine blade tip clearance delta 1, a high-pressure compressor blade tip clearance delta 2, a minimum thrust Fm in a take-off process, a total oil consumption TFC in the whole process, warm-up time delta t and a warm-up rotating speed NH in the engine process; then, on the basis of the samples, a prediction model for delta 1, delta 2, Fm and TFC by delta t and NH is established through an artificial neural network; and finally, by taking the minimum values of delta 1, delta 2 and Fm required by actual use as constraints, selecting a combination of the lowest required machine warming time and machine warming rotating speed by utilizing an epsilon-constraint method, and if the combination is not unique, selecting a combination corresponding to the minimum TFC from a result to finish optimization of the machine warming process. According to the method, the artificial neural network is used for establishing the relation of the related variables along with the engine warming time and the engine warming rotating speed, the epsilon-constraint method is used for selecting the minimum required engine warming time under multiple constraints, and the engine warming process is scientifically optimized.

The invention discloses an axial flow compressor blade profile optimization method based on main and auxiliary agent models and a related device, and relates to the field of compressor blade design, and the method comprises the steps: generating a plurality of design parameter groups based on to-be-optimized design parameters and a parameter adjustable range of a to-be-optimized axial flow compressor blade by using a data sampling algorithm, outputting a blade profile performance prediction value corresponding to each design parameter group by using the main and auxiliary combination agent model, screening a plurality of alternative design parameter groups based on a comparison result of each blade profile performance prediction value and an initial performance reference, and performing computational fluid dynamics simulation; and determining the alternative design parameter group corresponding to the optimal simulation performance parameter as a blade profile optimization parameter group. According to the method, the invalid risk of the design parameter group is reduced by using the adjustable range of the parameters, the performance prediction precision is improved based on the flow field characteristic parameters by using the main and auxiliary combination agent model, finally, the blade profile optimization parameter group is determined based on the simulation result of the screened alternative design parameter group, and the prediction precision is further improved.