47 results about "AxSTREAM" patented technology

The invention provides a one-dimensional pneumatic design method and device for an axial flow compressor, and belongs to the field of axial flow compressor pneumatic design. The method comprises the following steps: taking values of a plurality of design variables as the state of a reinforcement learning agent; the intelligent agent outputs the adjustment amount of the design variable according to the state, and the adjustment amount serves as the action executed by the intelligent agent; applying the action to the value of the current design variable to obtain an updated design variable; utilizing a one-dimensional inverse problem design program to generate a one-dimensional pneumatic design scheme of the gas compressor; utilizing a one-dimensional normal problem analysis program to output performance indexes; constructing a reward function according to the performance indexes; based on feedback provided by the reward function, a depth deterministic strategy gradient algorithm is adopted to train the intelligent agent; and performing one-dimensional pneumatic design of the gas compressor by using the trained intelligent agent. According to the method and device provided by the invention, the problems that the one-dimensional design of the axial flow compressor depends on experience, the efficiency is low, automatic optimization is difficult and the response is slow can be solved.

The utility model relates to the technical field of steam power generation turbines, in particular to a mixed flow type saturated steam power generation turbine which comprises a cylinder, the cylinder comprises a vertical inlet cavity and a horizontal outlet cavity which are communicated, and reinforcing ribs are arranged at the positions, corresponding to the joint of the two cavities, of the inner wall of the cylinder. A protruding structure at the bottom of the side, away from the horizontal outlet cavity, of the outer wall of the air cylinder is fixedly connected with a gearbox. The stationary blade assembly comprises a first-stage radial flow stationary blade fixedly arranged on the inner wall of the vertical inlet cavity and a second-stage axial flow stationary blade fixedly arranged on the reinforcing ribs; the rotor assembly comprises a rotating part connected with the high-speed shaft of the gear box, a first-stage radial flow vane impeller and a second-stage axial flow vane impeller, wherein the periphery of the rotating part is sleeved with the first-stage radial flow vane impeller and the second-stage axial flow vane impeller. The radial flow turbine and the axial flow turbine are combined to form the mixed-flow turbine, so that the working capacity of a single cylinder is improved, the power generation efficiency is improved, the cost is saved, and the unit size is reduced.

The application provides a high-reliability one-dimensional inverse problem aerodynamic design method of an axial turbine, which is used for providing a better design method for the turbine in a one-dimensional inverse problem design link. The technical scheme is as follows: on the basis of the original, non-simplified processing is performed on core design parameters in turbine dimensionless parameters, such as inverse force degree, load coefficient, flow coefficient and the like, new inverse problem design calculation is performed on the processing, and a new inverse problem calculation process is reconstructed according to new definition formula.

The application discloses a high-pressure-ratio transonic axial flow compressor, which comprises a hub, front-row rotor blades, rear-row rotor blades and stator blades; the rear-row rotor blades are arranged between the front-row rotor blades and the stator blades; a plurality of front-row rotor blades and a plurality of rear-row rotor blades are uniformly arranged on the hub along a circumferential direction; and the front-row rotor blades and the rear-row rotor blades one-to-one correspond to form tandem rotors. The application realizes shock wave supercharging through the front-row rotor blades, and the rear-row rotor blades complete large airflow deflection; meanwhile, the application adopts an adsorption type stator to reduce or prevent airflow separation in a blade channel, thereby significantly improving a compressor stage pressure ratio and improving aerodynamic performance of the compressor. The application can realize a higher stage pressure ratio, and in the case of high inlet Mach number, high load and large airflow deflection angle, the application overcomes the problem that a high stage pressure ratio and efficiency are difficult to realize due to the fact that flow separation in the compressor cannot be controlled in the prior art.

This application discloses a method for optimizing the hub profile of an axial flow fan blade. The method includes: real-time acquisition of fan operating conditions to obtain the current fan speed and outlet back pressure, forming an operating condition vector; inputting the operating condition vector into a pre-trained adaptive prediction model, which outputs the optimal hub profile parameter vector corresponding to the current operating condition; the optimal hub profile parameter vector is set as a dynamic variable related to the operating condition vector, and the optimal hub profile parameter is pre-obtained based on a multi-objective comprehensive performance evaluation function with blade passing frequency sound pressure level and fan aerodynamic efficiency as optimization objectives, through adaptive optimization under different operating conditions; and dynamically adjusting the hub profile of the physical axial flow fan according to the optimal hub profile parameter. Thus, real-time adaptive adjustment of the axial flow fan hub profile to operating conditions is achieved.

This invention discloses a rotor blade of a segmented stacked axial compressor and its design method. The design method includes: determining the axial position of the stacking line; determining the circumferential position of the stacking line: the stacking line is S-shaped in the circumferential direction, and the stacking line includes four control points A, B, C, and D sequentially from the blade root to the blade tip along the height direction; the coordinates of the centroid positions of each basic airfoil section in the first interval from point B to point C conform to a specific formula; and determining the shape of the stacking line based on the determined axial and circumferential positions. This invention, by setting the stacking line of the rotor blade to be S-shaped in the circumferential direction, generates a reverse pressure gradient in the radial direction, causing the gas at both ends to migrate towards the blade center, thereby improving the flow in the end region. This reduces the influence of secondary flow in the blade tip region; and by setting a specific function, the circumferential offset of the stacking line can be controlled by constructing a simple equation, improving the computational efficiency of optimizing the airfoil.

The invention relates to an aerodynamic stability quantification method and system based on flow mechanism and deep learning coupling, and the method comprises the steps: compressing the high-dimensional point cloud data of a manufactured blade into a low-dimensional basic mode based on principal component analysis, and effectively relieving the variable dimension disaster problem caused by geometric uncertainty; and then, by taking the low-dimensional fundamental mode weight as input, directly embedding the key physical characteristic, namely the blade tip leakage flow rate ratio, into a deep neural network hidden layer and taking the gas compressor stability margin variable quantity as output, constructing a physical constraint and data driving collaborative optimization framework, and remarkably improving the prediction precision of the pneumatic stability of the gas compressor under the small sample condition. According to the method, a quantification tool with high precision and physical credibility is provided for solving the problem of performance degradation caused by geometric deviation of the CAES multi-stage axial flow compressor under the non-design working condition, and key technical support is provided for achieving robustness design of the CAES multi-stage axial flow compressor.

This invention relates to the field of aerodynamic design technology for multi-stage axial compressors, and discloses a design method and system for passive stability enhancement of a multi-stage axial compressor through self-circulation. By calculating the aerodynamic performance of the multi-stage axial compressor and evaluating engine stability, the method identifies operating conditions where the multi-stage axial compressor has insufficient stability margin. Unsteady flow field simulations are then conducted under these conditions to determine the first stage stall. For the first stage rotor tip stall, a self-circulating casing is used for passive stability enhancement of the multi-stage compressor. The self-circulating casing structure is derived from sensitivity analysis of its design parameters, selecting the optimal design parameters to ensure an increase in the stability margin of the multi-stage axial compressor across the entire speed range. This satisfies the stability margin requirements of multi-stage axial compressors and avoids the problem of insufficient stability margin in high-load multi-stage axial compressors across the entire operating speed range.

The invention discloses a composite mixed-flow turbine, which belongs to the technical field of turbines, and mainly comprises a volute, a flow guide plate and a flow guide plate, the air inlet cone is mounted in the volute casing; the rotating piece is mounted on the air inlet cone; the impeller is installed on the rotating piece, multiple layers of blades are arranged on the impeller, the blades in part of layers are composite blades, the blades in part of layers are axial flow blades, and the blade layers with the axial flow blades are arranged adjacently; the length of the projection of a blade root chord D of each axial flow blade on the axis of the impeller is the projection length H, and the distance between adjacent layers with the axial flow blades is 1 / 5H-1 / 3H; and the tail cone is mounted in the volute casing, and the tail cone corresponds to the impeller. The turbine solves the problems that when fluid passes through an existing turbine, large air volume and high air pressure cannot be provided at the same time in a small space size, and turbulent flow and too large noise are generated at the same time.

This invention belongs to the technical field of compressor aerodynamic stability analysis. It proposes a deterministic learning-based method and system for analyzing the aerodynamic stability of axial compressors. Using pulsating pressure data during the aerodynamic instability development process of an axial compressor, a deterministic learning identification algorithm based on radial basis function neural networks is used to model the nonlinear dynamics of the compressor's internal flow field, thereby obtaining dynamic diagrams of normal and instability precursor states. Dynamic indices are extracted from these diagrams to construct dynamic feature vectors describing the compressor's aerodynamic stability. Based on the dynamic feature vectors corresponding to different operating states, the dynamic classification boundary between normal and instability precursor states is determined. The distance between the dynamic feature vector of the compressor data under test and the dynamic classification boundary is calculated to determine the compressor's operating state. This invention enables early warning of aerodynamic instability and has good interpretability and engineering application value.

The application belongs to the technical field of turbine blade design. The application provides a turbine blade parameterized modeling method and system based on integrated design of blade end wall. The complete three-dimensional turbine blade geometric surface is directly generated by NFFD grid in the embodiment of the disclosure, so that the high-order smooth transition between the blade and the end wall is easy to realize. The method not only supports local modification of the blade geometry, but also provides rich geometric modification deformation parameters, which facilitates determination of the adjustment range of the parameters and ensures that unreasonable geometric shapes do not occur. In the optimization design process, no additional constraint conditions need to be set, so that a flexible and efficient optimization process is realized. In addition, the method is suitable for modeling and parameterization of axial turbine blades for various purposes, and has good regulation and control effect on the end region secondary flow.

An end wall self-adaptive jet device of an axial flow compressor. It is installed on the outer surface of the casing corresponding to the position of the stator blade, which is a circular tapered pipe formed by sweeping along the center line, the center line is fitted by a Bezier curve, one end is an air inlet, the air inlet penetrates the casing behind the leading edge of the stator blade and closely adheres to the pressure surface of the stator blade, the other end is an air outlet, the air outlet penetrates the casing behind the middle of the axial chord length of the stator blade and is close to the suction surface of the stator blade. The effect of the application is that the pressure surface and the suction surface of the stator blade on the axial flow compressor are connected, the pressure difference between the air inlet and the air outlet forms a high-energy jet acting on the corner separation area, and the self-adaptive adjustment can be realized according to the change of the working condition of the axial flow compressor. Under suitable design parameters, it can effectively act on the corner flow field of the stator blade, reduce the range of corner separation, reduce the total pressure loss, improve the load of the stator blade, and improve the total pressure ratio and isentropic efficiency under small flow working condition.

The present application relates to the technical field of axial flow turbine, especially to a large expansion ratio high-efficiency axial flow turbine, which comprises a turbine hub and turbine blades, the turbine blade inlet tip wheel diameter is, the turbine blade outlet tip wheel diameter is, the turbine blade top axial chord length is, the relationship among the turbine blade inlet tip wheel diameter, the turbine blade outlet tip wheel diameter and the turbine blade top axial chord length is = 0~0.364, in this way, the traditional long blade pull wire design is abandoned, the blade height is limited, the blade root section is increased to reduce the root stress, the blade tip section area is greatly reduced, the intermediate section area is slightly smaller to improve the flow capacity, the wedge angle is optimized, the shock loss is reduced, the efficiency is improved, and the technical problem of the prior art that the turbine is designed as a long blade, the long blade needs to adopt a pull wire to ensure the strength, but the pull wire structure reduces the turbine flow area, thereby reducing the turbine efficiency and increasing the assembly difficulty of the axial flow turbine is solved.

The application relates to a passage integrated design method for an axial flow blade of an aero-engine, and belongs to the technical field of aero-engine aerodynamic design. The method can couple and control the passage integrated design of the blade, an end wall and an angle area. Starting from passage geometric characteristics, non-dimensional conversion is carried out; control points, virtual control points and local deformation domains are regularly constructed in the non-dimensional flow field; the extended free deformation technology is used to carry out integrated control; the flow field after the control is converted into a three-dimensional Cartesian coordinate system again, so that the integrated design of the blade, the end wall and the angle area is realized. The application can ensure that the end wall can still meet the periodicity requirement after the control, solves the limitation that the end wall cannot be included in the deformation domain during the deformation of the traditional free deformation technology, provides a larger design space for the full three-dimensional design of the passage, and can improve the design efficiency of the axial flow fan, the compressor and the turbine.

The invention discloses an axial flow fan hydraulic cylinder overhauling device, which relates to the technical field of axial flow fans and comprises a supporting seat, a clamping mechanism and an adjusting mechanism. The clamping mechanism comprises a first clamping assembly and a second clamping assembly, and the first clamping assembly and the second clamping assembly are movably connected with the supporting base. The adjusting mechanism comprises a first adjusting assembly and a second adjusting assembly, the first adjusting assembly comprises a first driving part and a first driven part, the second adjusting assembly comprises a second driving part and a second driven part, the first driven part is in sliding fit with the first clamping assembly, and the second driven part is in sliding fit with the second clamping assembly. The first driving part and the second driving part are rotationally connected with the supporting base, the first driving part is in meshing transmission with the first driven part, and the second driving part is in meshing transmission with the second driven part. According to the scheme, manpower cost and a large amount of investment of maintenance equipment resources can be saved, and potential risks caused by misoperation in the traditional maintenance process can be avoided.

The invention discloses an intelligent surge fault early warning method for a multi-stage high-pressure-ratio axial flow compressor of an aero-engine, and belongs to the technical field of aero-engine fault prediction. Firstly, pressure signals of the aero-engine in various operation states are collected to obtain original data, and a graph network is constructed; secondly, preprocessing the original data, and dividing the original data into a training set and a verification set; then, constructing a graph attention physical information neural network model composed of a graph attention layer, a probability prediction network and a physical information prediction network; training a graph attention physical information neural network model; then, verifying and finely adjusting the graph attention physical information neural network model; and finally, surge fault prediction is carried out on the multi-stage high-pressure-ratio axial flow compressor, and a prediction result is output to a surge early warning system. According to the method provided by the invention, the generalization ability of the model can be remarkably improved; an early warning signal can be given in advance, and a high-reliability solution is provided for surge prevention and control of the multi-stage high-pressure-ratio axial flow compressor of the aero-engine.

The invention belongs to the technical field of pneumatic shape data mining and design optimization, and relates to an axial flow compressor full-working-condition optimization method and system. According to the method, the design variables having significant influence on the performance indexes and the influence directions and the influence degrees of the significant variables on the performance indexes are analyzed through the constructed mapping relation between the design variables and the performance indexes, so that the optimization problem has interpretability, and meanwhile, by analyzing the relation of the change trends among the multiple performance indexes, the optimization efficiency is improved. A performance index having a conflict relationship with a main optimization target is used as a constraint condition of the main optimization target, and a multi-working-condition multi-target optimization problem is converted into a form of one optimization target and a plurality of optimization constraints, so that the optimization problem is simplified; the restrictive relation between the stall margin under the partial rotating speed and the peak efficiency under the designed rotating speed in traditional gas compressor optimization is effectively solved, and comprehensive improvement of the performance of the gas compressor is achieved.

The invention discloses an H-shaped rotating handle and eccentric sphere transmission structure for a rotatable guide vane of a gas turbine compressor, and relates to the technical field of gas turbines and axial flow fans. The problems that a rotating handle of a transmission structure for the rotatable guide vane in an existing gas turbine compressor is distorted and deformed due to stress, and a rotating pair part is abraded and deformed in long-term work are solved. One end of the H-shaped rotating handle is fixed to the head of the rotatable guide vane, the rotatable guide vane only rotates in the plane, the other end of the H-shaped rotating handle is in contact connection with the eccentric ball, two degrees of freedom are achieved in the vertical axis and the axial direction, and the problem that the rotating handle is distorted and deformed due to stress is solved. The eccentric ball is fixed on the rotating ring, the eccentric ball rotates along with the rotating ring, the inner plane of the H-shaped rotating handle rotates along the eccentric ball slideway and together with the eccentric ball and the rotating ring, the H-shaped rotating handle and the eccentric ball form a rotating pair, and due to the arrangement of the eccentric ball, it is guaranteed that the rotating pair cannot be abraded or deformed during long-term work. The invention is applicable to the field of gas turbines.

The invention discloses a performance improvement optimization design method and system for a movable blade adjustable axial flow fan. The method comprises the steps that firstly, the number of blade profile modeling sections of an outlet guide blade of the movable adjustable axial flow fan is selected; secondly, giving a specific blade profile section two-dimensional curve modeling method for each section; and finally, completing modeling of a three-dimensional model of the outlet guide vane of the dynamically adjustable axial flow fan, and giving the number of the outlet guide vanes. According to the method, under the condition that the overall structure of the movable blade adjustable axial flow fan is kept unchanged, the actual operation efficiency and actual output of the fan can be improved through the method for conducting optimization design on the outlet guide blades of the fan. The performance improvement optimization design method for the movable blade adjustable axial flow fan has the advantages of being low in investment cost, short in investment recovery age limit and the like, and is suitable for large-scale application and popularization in the market.

The application discloses a rotor blade of an axial flow compressor and a method for obtaining a stacking line of the rotor blade. The method comprises the following steps: determining a circumferential position of the stacking line; the stacking line is S-shaped in the circumferential direction, and the stacking line is formed by controlling four points A, B, C and D which are sequentially preset in the height direction from the blade root to the blade tip; the coordinates of each sectional center of gravity circumferential position point conform to a specific formula; determining an axial position of the stacking line; the coordinates of each sectional center of gravity axial position point conform to a specific formula; and determining a line type of the stacking line according to the determined axial position and the circumferential position of the stacking line. The stacking line of the rotor blade is S-shaped in the circumferential direction, so that an adverse pressure gradient can be generated in the radial direction, thereby weakening the influence of the secondary flow in the blade tip area; and a specific function is set to control the circumferential and axial offset of the stacking line by constructing a simple equation, thereby improving the calculation efficiency of the optimized blade type.

The invention discloses a method, a device and equipment for predicting the performance of a multistage axial flow compressor under all working conditions, and relates to the technical field of impeller mechanical performance prediction.The method comprises the steps that firstly, a plurality of loss attack angles representing blade working angle critical values of each stage of blade under different working conditions are obtained; the obtained loss attack angle can more truly simulate the physical phenomenon that the loss changes sharply along with the working condition, then main flow losses covering the pressure ratio and efficiency during operation of the interior of the gas compressor are systematically integrated, and the obtained loss attack angle is adopted to correct the total loss obtained after the main flow losses are added. According to the correction, the physical phenomenon that the real simulation loss changes sharply along with the working condition can be coupled to the main flow loss, it is ensured that the main flow loss is represented more reasonably in the physical sense, dynamic and nonlinear calibration of a traditional empirical loss model is achieved, random volatility in prediction at the present stage is thoroughly avoided, and the prediction accuracy is improved. Therefore, the accuracy of predicting the all-condition one-dimensional characteristics of the axial flow compressor is greatly improved.

The application discloses a self-circulation jet structure of a compressor using an end area pressure difference, relates to the technical field of auxiliary work of an axial flow compressor, and comprises a structure main body; the structure main body is formed by being connected with a connecting ring and a conical cover; one end of the connecting ring is provided with an arc-shaped strip one and an arc-shaped strip two; a connecting plate is fixed to the outer wall of the one end of the connecting ring; the arc-shaped strip one is movably connected to one end of the connecting plate through a movable column one; the arc-shaped strip two is movably connected to one end of the connecting plate through a movable column two; one end of the arc-shaped strip one is fixedly provided with a connecting lug one; one end of the arc-shaped strip two is fixedly provided with a connecting lug two; a threaded hole one is formed in the one end of the connecting lug one; a threaded hole two is formed in the one end of the arc-shaped strip two; and a fixing bolt one is screw-connected in the threaded hole one and the threaded hole two. The application is relatively simple and convenient when the structure main body and the axial flow compressor are disassembled, and is also convenient for maintaining the parts inside the structure main body.

The application relates to a design method for deriving and developing a downward flow path of an aero-engine axial flow compressor, which comprises the following steps: step one, downward pressing of compressor inlet and outlet hubs, namely, downward pressing of inner flow paths of the compressor inlet and outlet; step two, re-determination of the compressor hub flow path according to the downward pressing amount of the compressor inlet and outlet hubs; step three, re-determination of the compressor casing flow path while keeping the compressor flow path area unchanged; step four, re-determination of the design rotating speed of the compressor while keeping the compressor rotating speed inlet blade tip tangential velocity unchanged; step five, adjustment of the blade profile of each stage of rotor and stator blades while keeping the compressor stage pressure ratio, efficiency and radial distribution unchanged; step six, adjustment of the inlet pre-whirl angle of each stage while keeping the compressor rotor counterforce unchanged; and step seven, checking of the radial distribution of the diffusion factors of each stage of the compressor rotor and stator, and if the radial distribution exceeds the engineering applicable value, returning to step one, adjusting the downward pressing amount of the compressor inlet and outlet hubs and performing iterative optimization.

The invention provides a deformation control process for a 3D printing radial split axial flow casing, and relates to the technical field of aero-engine part machining. In order to solve the problems of non-uniform allowance of a 3D printing blank, large machining deformation, datum conversion error accumulation and the like, the process sequentially comprises the core procedures of front and back mounting edge datum milling, linear cutting and halving, datum repairing, joint surface and hole rough milling, two times of vacuum stress relief, rough turning and rough milling of the appearance, joint surface and hole finish milling, finish machining and the like by optimizing the procedure flow and sequentially comprises the core procedures of front and back mounting edge datum milling, linear cutting and halving, datum repairing, joint surface and hole finish milling, finish machining and the like. The method is characterized in that machining allowance is reasonably distributed, benchmark establishment is attached to a design benchmark, vacuum stress relief treatment is alternately conducted in the stage from rough machining to finish machining, and the key procedure is kept in a two-section casing combined state for machining. According to the process, the problem of scrapping caused by insufficient machining allowance of the 3D printer case is effectively solved, the dimensional precision and the form and location tolerance of parts are controlled within 0.02 mm, the machining efficiency is improved, the product quality is stabilized, the manufacturing cost is reduced, and the process is suitable for batch production of high-precision radial split axial flow cases.

This invention belongs to the field of axial flow fan technology, specifically relating to a method for designing the blade structure of an axial flow fan for nuclear power plants. The method involves selecting a basic model, scaling it up by an amplification factor x to obtain the target model, and introducing a Reynolds number correction factor K. Re And through the Reynolds number correction factor K Re Adjust the blade chord length of the target aircraft model to obtain the blade chord length parameter C. 新 ; through the Reynolds number correction factor K Re Adjust the blade installation angle of the target aircraft model to obtain the blade installation angle parameter β. 新 The blade is divided into n equal regions from the blade root to the blade tip, and an installation angle adjustment rule is established. The blade thickness of the target model is optimized by gradient to obtain the thickness distribution function t(r) along the spanwise direction of the blade. The blade structure of the target model is completed. This method can optimize the efficiency and service life of the scaled-up wind turbine and provide technical guidance for how to develop wind turbines of different sizes.

This application provides a support base for the stator vane adjusting ring of an ultra-large axial compressor. The support base is disposed between the housing and the adjusting ring to support the adjusting ring. The support base includes: a support frame disposed on the housing, with rollers disposed on the support frame and the rollers contacting the adjusting ring; and a fixing member passing through the support frame and connected to the housing to assemble the support frame onto the housing. This application, through the inclusion of a buffer assembly, allows the buffer assembly to undergo adaptive deformation under pressure when the housing expands. This deformation, combined with a buffer gap, absorbs and offsets the expansion, preventing excessive supporting stress due to thermal expansion differences. This effectively protects the thin-walled housing and adjusting ring of the ultra-large axial compressor from damage, while maintaining the concentricity of the adjusting ring and the housing.

The invention provides a tilt rotor aerodynamic performance calculation method, device and equipment under multiple flight states and a medium. The method comprises the steps that input conditions are determined; based on the momentum theory, an oblique inflow model and a blade tip loss correction Pandtl approximation function are introduced, a tension and torque calculation formula of the tilt rotor in the oblique inflow state is established, and input conditions are substituted; based on a blade element theory, a tension and torque calculation formula of the tilt rotor at different spanwise positions is established, and input conditions are substituted; a tension and torque calculation formula based on the momentum theory and a tension and torque calculation formula based on the blade element theory are combined, and induced velocity distribution of different positions of a rotor disc is obtained through iterative solution; based on induced velocity distribution, the total tension and the total torque of the whole rotor system are calculated, so that the problems that an existing tilt rotor aerodynamic performance calculation method can only cover two axial flow states of hovering and high-speed cruising, an effective model for a tilt forward flight key transition state is lacked, and the calculation precision of a single theory is insufficient are solved.

The invention relates to the technical field of gas compressor surge judgment, and discloses a surge judgment method based on an axial flow gas compressor test piece performance test, which comprises the following steps: S1, performing core judgment: in a normal operation stage of a gas compressor test piece, performing core judgment; collecting pulsating pressure data of an outlet of the gas compressor test piece and / or collecting flow data of an inlet of the gas compressor test piece and / or measuring pulsating static pressure data of the gas compressor test piece, and core-judging surge; s2, auxiliary verification is carried out, in the normal operation stage of the gas compressor test piece, rotating speed data of the gas compressor test piece and / or vibration acceleration of a front casing and a rear casing of the gas compressor test piece and / or total temperature data of an outlet of the gas compressor test piece are / is collected, and surge is verified in an auxiliary mode; and S3, when the step S1 is established and verification in the step S2 is established, it is judged that the compressor test piece enters the surge state. According to the invention, test safety can be guaranteed, test data can be ensured to be effective, and the effect and efficiency of the performance test of the gas compressor test piece are effectively improved.