Air compressor rotor testing method and testing device

Abstract

The application discloses an air compressor rotor testing method and testing device, relates to the technical field of air compressor rotor testing, and realizes accurate positioning of the position of rotor mass imbalance by collecting vibration signal data of the rotor at multiple rotating speeds, analyzing by using a fast Fourier transform algorithm, extracting frequency and phase distribution, and performing weighted analysis on the phase distribution to extract initial position coordinates of uneven mass distribution. The least square method is used to fit the offset to obtain mass deviation coordinates, generate an initial counterweight adjustment scheme, combine the gradient descent algorithm to optimize the initial counterweight parameters, obtain an optimized counterweight adjustment scheme, use the particle swarm optimization algorithm to re-iterate the counterweight parameters of the optimized counterweight adjustment scheme, obtain a target counterweight scheme, and ensure that the vibration signal of the rotor meets the vibration balance standard. The application improves the dynamic balance testing efficiency and precision of the air compressor rotor and ensures the stability of the operation of the rotating mechanical equipment.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of air compressor rotor testing, and in particular to an air compressor rotor testing method and testing device. BACKGROUND

[0002] As a core component of the compressor, the dynamic balance of the air compressor rotor directly affects the stability and service life of the equipment, and is an important research direction in the field of industrial manufacturing. If the rotor has uneven mass distribution during high-speed rotation, it will cause eccentric vibration, leading to accelerated equipment wear and even failure, which seriously affects production efficiency and safety. Therefore, developing a high-precision rotor dynamic balance testing method and device is of key significance to improving the performance of air compressors.

[0003] Current testing methods mainly rely on traditional vibration measurement and manual weight adjustment, and generally have the problems of low efficiency and insufficient precision. The traditional method often needs to be adjusted multiple times, the test cycle is long, and the adaptability to complex rotor structures is poor. Especially in the face of diversified rotational speed and load conditions, it is difficult to quickly capture small vibration signals and accurately determine the position of mass deviation. In addition, the existing technology lacks real-time and automation capabilities when dealing with nonlinear vibration responses, resulting in a reliance on manual experience during the adjustment process, which makes it difficult to meet the high-precision industrial demand.

[0004] The core challenge of dynamic balance testing is how to accurately measure and analyze the vibration characteristics of the rotor at different speeds, and to achieve rapid and automatic adjustment of the weight. Vibration characteristic measurement requires capturing small signals through sensors, but the vibration signal is affected by factors such as rotational speed, geometric shape, and support stiffness when the rotor is rotating at high speed, showing complex nonlinear characteristics, making it difficult to directly determine the specific position of uneven mass distribution. For example, in a certain air compressor rotor test, the sensor may detect significant vibrations, but due to inaccurate frequency and phase analysis, repeated trials are often required when adjusting the weight, which is time-consuming and ineffective. More complex is that adjusting the weight position and mass requires comprehensive consideration of the dynamic response of the rotor and the actual working conditions, and the traditional method is difficult to calculate accurate weight values in real time, resulting in low testing efficiency.

[0005] Therefore, how to develop a self-adaptive correction algorithm based on real-time vibration frequency and phase analysis to automatically calculate and adjust the weight parameters has become a key problem to improve the efficiency and precision of air compressor rotor dynamic balance testing. SUMMARY

[0006] The present application provides an air compressor rotor testing method and testing device to realize real-time vibration frequency and phase analysis-based automatic calculation and adjustment of weight parameters, and to improve the efficiency and precision of air compressor rotor dynamic balance testing.

[0007] The present application provides an air compressor rotor testing method executed by a computer, comprising:

[0008] obtain vibration signal data of the rotor at multiple rotation speeds, analyze the vibration signal data using a fast Fourier transform algorithm to obtain vibration frequency and phase distribution;

[0009] If the vibration frequency exceeds a preset frequency threshold, perform weighted analysis on the phase distribution to determine an initial position coordinate of uneven mass distribution;

[0010] Based on the initial position coordinate, use the least squares method to fit the offset of the rotor to obtain a mass deviation coordinate;

[0011] Based on the mass deviation coordinate, generate an initial counterweight adjustment scheme, and use a gradient descent algorithm to optimize the initial counterweight parameter of the initial counterweight adjustment scheme to obtain an optimized counterweight adjustment scheme;

[0012] Based on the counterweight parameter of the optimized counterweight adjustment scheme, perform dynamic response simulation in a simulation environment to obtain a simulation vibration signal;

[0013] If the simulation vibration signal exceeds a balance threshold, use a particle swarm optimization algorithm to re-iterate and update the counterweight parameter of the optimized counterweight adjustment scheme to obtain a target counterweight scheme;

[0014] The target counterweight scheme is used to be applied to the rotor for testing to make the balance state of the rotor reach a set standard.

[0015] The air compressor rotor testing method provided by the application further comprises:

[0016] Apply the target counterweight scheme to the rotor through an automatic actuator to obtain real-time vibration feedback signal;

[0017] If the vibration feedback signal contains residual vibration, perform secondary analysis on the vibration feedback signal to update the mass deviation coordinate and determine the feedback counterweight parameter;

[0018] Based on the feedback counterweight parameter, continuously iterate, optimize and real-time feedback adjust to generate a dynamic balance counterweight scheme, wherein the working state of the rotor reaches a set standard when the dynamic balance counterweight scheme is applied to the rotor.

[0019] The air compressor rotor testing method provided by the application, if the vibration frequency exceeds a preset frequency threshold, the phase distribution is analyzed to determine the initial position coordinate of uneven mass distribution, comprising:

[0020] If the vibration frequency exceeds a preset frequency threshold, obtain the vibration signal data of the rotor, and use a fast Fourier transform algorithm to calculate the vibration frequency value of the vibration signal data to obtain frequency data;

[0021] based on the frequency value of the frequency data exceeding the preset frequency threshold, generating a phase distribution matrix based on the phase distribution;

[0022] based on the phase distribution matrix, calculating a weighted phase value of the phase distribution matrix using a weighted analysis algorithm to determine a phase distribution feature;

[0023] comparing the phase distribution feature with a preset quality distribution model, fitting a mass distribution curve of the unbalanced mass of the rotor on the balance plane using a least squares method algorithm to determine an unevenness degree parameter, wherein the unevenness degree parameter is an evaluation index of the unbalanced state of the rotor;

[0024] based on the unevenness degree parameter, calculating a spatial deviation of the mass distribution to determine the initial position coordinates.

[0025] According to the air compressor rotor testing method provided by the application, based on the initial position coordinates, the offset of the rotor is fitted using the least squares method to obtain mass deviation coordinates, which includes:

[0026] based on the initial position coordinates and a preset coordinate system, the offset of the rotor relative to the center axis is calculated using the Euclidean distance calculation method to obtain an offset data set;

[0027] if the offset in the offset data set exceeds the preset offset threshold, the offset data set is denoised using a median filtering method to obtain a smoothed offset data set;

[0028] based on the smoothed offset data set, the offset is fitted using the least squares method to obtain an eccentric vector parameter;

[0029] based on the direction and amplitude information in the eccentric vector parameter, the mass deviation coordinates are determined using a vector decomposition method.

[0030] According to the air compressor rotor testing method provided by the application, based on the mass deviation coordinates, an initial counterweight adjustment scheme is generated, and the initial counterweight parameter of the initial counterweight adjustment scheme is optimized using a gradient descent algorithm to obtain an optimized counterweight adjustment scheme, which includes:

[0031] based on the mass deviation coordinates, a deviation vector is calculated to obtain an initial mass deviation distribution;

[0032] based on the initial mass deviation distribution, the counterweight mass and the counterweight position are initialized to determine the initial counterweight adjustment scheme and the initial counterweight parameter corresponding to the initial counterweight adjustment scheme;

[0033] If the error analysis result of the initial counterweight parameter is greater than a preset error threshold, the counterweight mass and the counterweight position of the initial counterweight parameter are iteratively updated by a gradient descent algorithm to obtain an optimized parameter.

[0034] Based on the optimized parameter, a mass deviation distribution is recalculated to obtain the optimized counterweight adjustment scheme.

[0035] According to the air compressor rotor testing method provided by the application, the counterweight parameter based on the optimized counterweight adjustment scheme is subjected to dynamic response simulation in a simulation environment to obtain a simulation vibration signal, which comprises:

[0036] The initial counterweight parameter is loaded in the simulation environment, and dynamic response simulation is performed to obtain vibration signal data;

[0037] Based on the vibration signal data, a signal extraction technique is used to extract the vibration characteristics to obtain vibration characteristic parameters;

[0038] If the vibration characteristic parameters exceed a preset balance threshold, the counterweight parameter of the optimized counterweight adjustment scheme is adjusted by a gradient descent algorithm to generate a new counterweight parameter;

[0039] Based on the new counterweight parameter, dynamic response simulation is performed again in the simulation environment to obtain updated vibration signals;

[0040] Based on the updated vibration signals, a signal processing technique is used to extract new vibration characteristics to determine the simulation vibration signal.

[0041] According to the air compressor rotor testing method provided by the application, if the simulation vibration signal exceeds the balance threshold, a particle swarm optimization algorithm is used to iteratively update the counterweight parameter of the optimized counterweight adjustment scheme to obtain a target counterweight scheme, which comprises:

[0042] Based on the simulation vibration signal, a Fourier transform is used to perform frequency domain decomposition to obtain frequency domain vibration characteristics;

[0043] If the amplitude of the frequency domain vibration characteristics exceeds the balance threshold, a signal processing algorithm is used to denoise the frequency domain vibration characteristics to obtain smoothed vibration characteristics;

[0044] Based on the smoothed vibration characteristics, a particle swarm optimization algorithm is used to iteratively update the counterweight parameter of the optimized counterweight adjustment scheme to generate the target counterweight scheme.

[0045] The application also provides an air compressor rotor testing device, which comprises:

[0046] The acquisition module is configured to acquire vibration signal data of the rotor at multiple rotation speeds, analyze the vibration signal data by using a fast Fourier transform algorithm, and obtain vibration frequency and phase distribution;

[0047] The analysis module is configured to, if the vibration frequency exceeds a preset frequency threshold, perform weighted analysis on the phase distribution to determine an initial position coordinate of the uneven mass distribution.

[0048] The fitting module is configured to, based on the initial position coordinate, fit the offset of the rotor by using a least square method to obtain a mass deviation coordinate.

[0049] The optimization module is configured to generate an initial counterweight adjustment scheme based on the mass deviation coordinate, optimize an initial counterweight parameter of the initial counterweight adjustment scheme by using a gradient descent algorithm, and obtain an optimized counterweight adjustment scheme.

[0050] The simulation module is configured to perform dynamic response simulation on the optimized counterweight adjustment scheme in a simulation environment based on a counterweight parameter of the optimized counterweight adjustment scheme to obtain a simulation vibration signal.

[0051] The update module is configured to, if the simulation vibration signal exceeds a balance threshold, re-iteratively update the counterweight parameter of the optimized counterweight adjustment scheme by using a particle swarm optimization algorithm to obtain a target counterweight scheme.

[0052] The target counterweight scheme is used to be applied to the rotor for testing, so that the balance state of the rotor reaches a set standard.

[0053] The air compressor rotor testing method and testing device provided by the application can solve the problem of uneven vibration distribution of the rotor caused by uneven mass distribution in high-speed rotation, by collecting vibration signal data of the rotor at multiple rotation speeds, analyzing the vibration signal data by using a fast Fourier transform algorithm, extracting frequency and phase distribution, and performing weighted analysis on the phase distribution to extract an initial position coordinate of the uneven mass distribution, so that the position of the mass imbalance of the rotor can be accurately positioned. The least square method is used to fit the offset to obtain a mass deviation coordinate, generate an initial counterweight adjustment scheme, and combine the gradient descent algorithm to optimize the initial counterweight parameter to obtain an optimized counterweight adjustment scheme. The optimized counterweight adjustment scheme is simulated in a simulation environment, and the particle swarm optimization algorithm is further used to re-iterate the counterweight parameter of the optimized counterweight adjustment scheme to obtain a target counterweight scheme, so that the vibration signal of the rotor can meet the vibration balance standard. The application realizes real-time vibration frequency and phase analysis, automatically calculates and adjusts the counterweight parameter, and makes the rotor reach a stable dynamic balance standard, so that the dynamic balance testing efficiency and precision of the air compressor rotor are improved, the vibration residual is reduced, the stability of the rotating mechanical equipment is ensured, the service life of the equipment is prolonged, and the dynamic balance use requirement is prolonged. BRIEF DESCRIPTION OF DRAWINGS

[0054] Figure 1 is one of flow schematic diagrams of the air compressor rotor testing method provided by the embodiment of the present application;

[0055] Figure 2 is one of flow schematic diagrams of the air compressor rotor testing method provided by the embodiment of the present application;

[0056] Figure 3 is one of flow schematic diagrams of the air compressor rotor testing method provided by the embodiment of the present application;

[0057] Figure 4 is one of flow schematic diagrams of the air compressor rotor testing method provided by the embodiment of the present application;

[0058] Figure 5 is one of flow schematic diagrams of the air compressor rotor testing method provided by the embodiment of the present application;

[0059] Figure 6 is one of flow schematic diagrams of the air compressor rotor testing method provided by the embodiment of the present application;

[0060] Figure 7 is one of flow schematic diagrams of the air compressor rotor testing method provided by the embodiment of the present application. DETAILED DESCRIPTION

[0061] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments of the present application. Based on the embodiments in the present application, all the other embodiments obtained by those skilled in the art without creative work fall within the protection scope of the present application.

[0062] With reference to Figure 1 The embodiment of the present application provides an air compressor rotor testing method, which comprises the following steps:

[0063] In step 100, vibration signal data of the rotor at multiple rotating speeds is acquired, and a fast Fourier transform algorithm is used to analyze the vibration signal data to obtain vibration frequency and phase distribution.

[0064] The vibration signal data of the rotor at multiple rotation speeds can be collected by a high-precision sensor array, and then the vibration signal data is converted into frequency domain by using a fast Fourier transform algorithm to obtain spectrum data. According to the spectrum data, the vibration frequency is extracted, and the amplitude and phase distribution of each frequency component are calculated. The core of this step is to locate the mass distribution defect of the rotor by dynamic vibration analysis. During the test, the vibration time domain signal of the rotor is first collected at multiple preset rotation speed conditions. This multi-rotation speed coverage strategy can comprehensively capture the response characteristics of the rotor under different dynamic states. Then, the vibration signal data is decomposed into frequency domain by using fast Fourier transform, and the time domain vibration waveform is converted into frequency domain representation, so that the main vibration frequency component of the rotor and the corresponding phase angle information are accurately extracted, and the vibration frequency and phase distribution are obtained, wherein the phase distribution reflects the space-time characteristics of each vibration source of the rotor in the circumferential direction.

[0065] For example, when collecting the rotor vibration signal data by using a high-precision sensor array, MEMS acceleration sensors can be arranged in the X, Y and Z directions of the rotor bearing seat, and vibration signals at rotation speeds of 1000 rpm, 2000 rpm and 3000 rpm are collected, and the sampling time is 10 seconds to generate time series data (10000 points per second, a total of 100000 points). The data is transmitted to the embedded processor by a 24-bit ADC converter through an I2C protocol. Then, the signal is processed by using a fast Fourier transform algorithm, which is realized by using a Cooley-Tukey algorithm, the input data points N=8192 (2 raised to the power of 13), and the time domain signal is decomposed into frequency domain by using a butterfly operation, and the frequency resolution Δf=10000 / 8192≈1.22Hz is calculated. When analyzing the spectrum, the main vibration frequency is extracted, for example, at 2000 rpm (33.33 Hz), a significant peak value of 33 Hz, 66 Hz (2 times frequency) and 100 Hz (3 times frequency) is observed, and the amplitude is 0.5g, 0.2g and 0.1g respectively. The phase distribution is calculated by using the complex result output by the fast Fourier transform algorithm to obtain the phase angle of each frequency component, for example, the phase at 33 Hz is 45°, and the phase at 66 Hz is 90°. Combined with the rotor dynamics model, the linear relationship between the frequency and the rotation speed is verified, and whether there is imbalance is judged.

[0066] In step 200, if the vibration frequency exceeds the preset frequency threshold, the phase distribution is analyzed by weighting to determine the initial position coordinates of the mass distribution imbalance.

[0067] When a certain vibration frequency component is detected to exceed a preset safety threshold, it indicates that the rotor has an abnormal excitation source, which is usually caused by uneven mass distribution. At this time, the weighted analysis mechanism is started: based on the reliability of phase data at different speeds and the size of vibration energy, dynamic weight distribution is performed on the phase distribution. The dynamic weight distribution can be a phase data weight coefficient, which strengthens the high-energy vibration section and weakens the noise interference area, so that the environmental noise and harmonic interference can be effectively stripped, and the initial angle position of the mass imbalance in the rotor circumferential coordinate system is accurately positioned. Therefore, the vibration frequency can be used to determine the high-energy vibration area and the noise interference area, and the phase data weight coefficient can be used for weighted analysis of the high-energy vibration area and the noise interference area, respectively, to obtain more accurate initial position coordinates of the uneven mass distribution. The initial position coordinates are used to guide the subsequent dynamic balance correction of the counterweight operation, and the initial position coordinates include the radius and angle of the mass distribution uneven point.

[0068] Step 300, based on the initial position coordinates, the offset of the rotor is fitted by using the least square method to obtain mass deviation coordinates;

[0069] After determining the initial position coordinates of the rotor mass distribution unevenness, a precise counterweight optimization process is further implemented. First, a mathematical model of the rotor spatial offset is established by using the least square method: by aggregating the detected vibration phase offset data at multiple speeds, a mass deviation distribution function in the circumferential direction of the rotor is constructed to fit the offset of the rotor by using the mass deviation distribution function. The least square method can effectively eliminate single-point measurement error interference, and through the mass deviation distribution function, a continuous offset trajectory of the actual mass center relative to the geometric center is fitted in the three-dimensional coordinate system, and finally the mass deviation coordinates representing the maximum imbalance point are output. The mass deviation coordinates include angle position information and spatial vector amplitude of the mass defect.

[0070] Step 400, based on the mass deviation coordinates, an initial counterweight adjustment scheme is generated, and the initial counterweight parameter of the initial counterweight adjustment scheme is optimized by using the gradient descent algorithm to obtain an optimized counterweight adjustment scheme;

[0071] An initial counterweight adjustment scheme is generated based on the mass deviation coordinates. This initial scheme includes the initial mass parameters of the counterweight blocks and the angle position of their installation. In short, the initial counterweight adjustment scheme includes both the counterweight mass and the counterweight position. To overcome the accuracy limitations caused by the nonlinearity of rotor dynamics in traditional counterweight schemes, a gradient descent algorithm is introduced for parameter optimization. Starting with the initial counterweight parameters, the algorithm calculates the residual vibration energy values ​​under different counterweight combinations, constructs a multi-dimensional response surface of the counterweight effect, and iteratively adjusts the counterweight mass and position along the negative gradient direction of this surface until the parameters automatically converge to the optimal solution that minimizes vibration energy, ultimately obtaining the optimized counterweight adjustment scheme. This dynamic optimization process based on the gradient descent algorithm can adaptively compensate for the influence of complex factors such as aerodynamic effects and changes in bearing stiffness.

[0072] Step 500: Based on the counterweight parameters of the optimized counterweight adjustment scheme, perform dynamic response simulation on the scheme in a simulation environment to obtain the simulated vibration signal;

[0073] After obtaining the optimized counterweight adjustment scheme, it can be virtually verified using a multiphysics coupled simulation platform. This platform, based on the dynamic equations and aerodynamic load model of the rotor-bearing system, imports the counterweight parameters from the optimized scheme for transient simulation across the entire speed range. It accurately reproduces the dynamic response characteristics of the rotor after the counterweight is applied, and outputs simulated vibration signals. These signals are used to evaluate the simulation effect of the optimized counterweight adjustment scheme. Therefore, the spectral characteristics of the simulated vibration signals are comparable to actual test data, enabling the prediction of rotor vibration behavior under real operating conditions. This eliminates the need for testing directly on the air compressor rotor, reducing rotor wear and improving simulation accuracy and effectiveness.

[0074] Step 600: If the simulated vibration signal exceeds the balance threshold, then the particle swarm optimization algorithm is used to iteratively update the counterweight parameters of the optimized counterweight adjustment scheme to obtain the target counterweight scheme.

[0075] The target counterweight scheme is applied to the rotor for testing so that the rotor's balance reaches a set standard.

[0076] If the equivalent amplitude of the simulated vibration signal exceeds the preset balance threshold, it indicates that the optimization scheme still has residual unbalance amount, and the counterweight scheme needs to be further optimized, wherein the balance threshold comprehensively considers the safety margin and process requirements, and represents the state threshold when the rotor reaches the dynamic balance state. At this time, the particle swarm optimization algorithm is started for parameter re-optimization. The particle swarm optimization algorithm maps the counterweight mass and counterweight position in the optimization counterweight adjustment scheme to the position vector of the particle in the multi-dimensional space, and takes the residual vibration energy value as the fitness function. The particle swarm searches in parallel in the parameter space through the group cooperation mechanism, dynamically adjusts the flight direction and step of the particle by using the dual guidance of the historical optimal solution and the global optimal solution. This distributed intelligent optimization can effectively jump out of the local optimal trap, gradually approach the global optimal solution in the iteration process, and finally output the target counterweight scheme that meets the balance standard.

[0077] The air compressor rotor test method and test device provided by the application can realize real-time vibration frequency and phase analysis, automatically calculate and adjust the counterweight parameters, make the rotor reach the stable dynamic balance standard, improve the dynamic balance test efficiency and precision of the air compressor rotor, reduce the residual vibration, ensure the stability of the rotating mechanical equipment operation, prolong the service life of the equipment, and prolong the dynamic balance use demand.

[0078] In one embodiment, referring to Figure 2 It also includes:

[0079] Step 700, applying the target counterweight scheme to the rotor through an automatic execution mechanism to obtain a real-time vibration feedback signal;

[0080] Step 800, if the vibration feedback signal contains residual vibration, performing secondary analysis on the vibration feedback signal, updating the mass deviation coordinates, and determining the feedback counterweight parameters;

[0081] At step 900, based on the feedback weight parameter, continuously iteratively optimize and real-time feedback adjustment, generate a dynamic balance weight scheme, wherein the working state of the rotor reaches the set standard when the dynamic balance weight scheme is applied to the rotor.

[0082] By adjusting the rotor according to the target weight scheme through the automatic execution mechanism, and collecting the vibration data feedback by the rotor, the real-time vibration feedback signal is obtained. Then, it is detected whether the vibration feedback signal contains residual vibration. The vibration feedback signal can be analyzed by the fast Fourier transform algorithm to obtain the vibration frequency characteristic, and then it is determined whether the vibration feedback signal contains residual vibration by whether the vibration frequency characteristic exceeds the preset range. It should be noted that if the vibration frequency characteristic exceeds the preset range, it means that the vibration feedback signal contains residual vibration. Further, the weight scheme adjustment mechanism can be that if it is detected that the vibration frequency characteristic exceeds the preset range, the weight correction amount is calculated; the weight parameter of the target weight scheme is updated according to the weight correction amount, the updated vibration data is collected, and it can also be judged whether the updated vibration data meets the dynamic balance state by the support vector machine algorithm.

[0083] If it is detected that the vibration feedback signal contains residual vibration, the vibration signal is analyzed in the frequency domain by Fourier transform to obtain the vibration frequency component. According to the vibration frequency component, the main vibration mode is extracted by principal component analysis to determine the mass deviation characteristic. If the mass deviation characteristic exceeds the preset threshold, the deviation data is fitted by the least square method to calculate the deviation coordinate value. According to the deviation coordinate value, the mass deviation coordinate is updated by the linear interpolation method to obtain the updated mass deviation coordinate. The feedback weight parameter is generated by the updated mass deviation coordinate. If the feedback weight parameter and the historical parameter difference exceed the preset range, the feedback weight parameter is optimized and adjusted by Kalman filtering to obtain the final adjustment value, and the dynamic balance weight scheme is generated.

[0084] In another embodiment, when the target weight scheme is applied to the rotor by the automatic execution mechanism, the vibration feedback signal of the rotor during operation is obtained. Then, the vibration feedback signal is analyzed by the fast Fourier transform to obtain the unbalance frequency component. According to the unbalance frequency component, the initial weight position and mass are calculated to determine the first intermediate weight scheme. The first intermediate weight scheme is verified by simulation to obtain intermediate simulation vibration data. If the intermediate simulation vibration data and the preset standard deviation are greater than the preset threshold, the first intermediate weight scheme is iterated by the gradient descent algorithm to obtain the second intermediate weight scheme. The weight position and configuration mass of the rotor are adjusted according to the second intermediate weight scheme to obtain real-time vibration data. If the real-time vibration data meets the preset standard, it is judged that the balance state is stable, and the final weight scheme is output as the second intermediate weight scheme.

[0085] The embodiment realizes full-process automatic closed loop of virtual optimization, entity execution and online feedback, eliminates the limitations of traditional dynamic balancing relying on manual trial and error, shortens the balancing correction period and improves optimization efficiency through real-time data feedback decision-making. And through the secondary analysis module, dynamic compensation of uncertain interference is realized, effectively separating the steady-state imbalance and transient interference.

[0086] In one embodiment, referring to Figure 3 , if the vibration frequency exceeds the preset frequency threshold, the initial position coordinates of the uneven mass distribution are determined by performing weighted analysis on the phase distribution, comprising:

[0087] Step 201, if the vibration frequency exceeds the preset frequency threshold, the vibration signal data of the rotor is obtained, and the vibration frequency value of the vibration signal data is calculated by using the fast Fourier transform algorithm to obtain the frequency data;

[0088] Step 202, based on the frequency value of the frequency data exceeding the preset frequency threshold, a phase distribution matrix is generated based on the phase distribution;

[0089] Step 203, based on the phase distribution matrix, a weighted phase value of the phase distribution matrix is calculated by using a weighted analysis algorithm to determine the phase distribution characteristics;

[0090] Step 204, compare the phase distribution characteristics with the preset mass distribution model, and use the least squares method algorithm to fit the mass distribution curve of the unbalanced mass of the rotor on the balance plane to determine the uneven degree parameter, wherein the uneven degree parameter is an evaluation index of the unbalanced state of the rotor;

[0091] Step 205, based on the uneven degree parameter, the spatial deviation of the mass distribution is calculated to determine the initial position coordinates.

[0092] When the vibration frequency exceeds the preset safety threshold, a multi-level diagnostic protocol is automatically triggered. First, the vibration signal data of the rotor in the full speed range is obtained, and the fast Fourier transform is used for real-time frequency spectrum decomposition to extract frequency data containing the fundamental frequency, multiple frequency and high-order harmonic. After the frequency data is filtered by a threshold filter, only the over-standard frequency band is retained to enter the deep analysis channel. For the phase information corresponding to the over-standard frequency, a phase distribution matrix coupled in space and time is constructed. The phase distribution matrix takes the speed gradient as the longitudinal dimension and the sensor array spatial coordinates as the transverse dimension to form a dynamic topological mapping of the rotor surface vibration phase. Based on the signal-to-noise ratio and vibration energy entropy value of each node in the phase distribution matrix, a weighted phase value is calculated by using a weighted analysis algorithm: higher weight is given to high-confidence measurement points, and phase distortion caused by electromagnetic interference or bearing clearance is automatically attenuated to obtain phase distribution characteristics representing the nature of mass defects. The weighted analysis algorithm can be an adaptive fuzzy weighted algorithm.

[0093] The phase distribution feature is input into a preset mass distribution model of the rotor, which is embedded with rigid body dynamics equations and material density distribution rules. The residual field of the measured phase and the theoretical phase is fitted by the least square method, and a continuous mass distribution probability curve is reconstructed in the balancing plane of the rotor. The gradient extreme point and the curvature radius of the mass distribution probability curve jointly generate the unevenness degree parameter, wherein the unevenness degree parameter is a standardized measurement of the mass eccentricity. Finally, the vector synthesis operation is performed based on the unevenness degree parameter, the offset angle and the radial deviation of the mass core are calculated in the polar coordinate system, and the initial position coordinates available for engineering are output.

[0094] For example, assuming that the vibration frequency is collected in real time through a sensor, the preset threshold is set to 50 Hz, the system detects that the current vibration frequency is 60 Hz, which exceeds the threshold, triggering the phase distribution weighted analysis. First, the phase data of the vibration signal is collected, the time domain signal is converted into the frequency domain using Fourier transform, the phase distribution matrix is obtained, and the matrix is assumed to be [30°, 45°, 60°, 90°], corresponding to four key points of the equipment. The weighted analysis adopts the weighted average algorithm, and the weights are determined according to the historical vibration contribution rate of each point, for example, the weight vector is [0.4, 0.3, 0.2, 0.1]. The weighted phase is calculated as follows: (30°×0.4+ 45°×0.3+60°×0.2+90°×0.1)=46.5°. To determine the initial position of the mass distribution unevenness, the system compares the weighted phase with the standard phase library, and the standard library stores the phase distribution when the equipment is normally running, for example, the standard value is 20°. The deviation is calculated as follows: 46.5°-20°=26.5°, which is greater than the threshold 5°, indicating that there is mass unevenness. Combined with the geometric model of the equipment, assuming that the equipment is a disc with a radius of 0.5 m, the mass distribution unevenness position is mapped through the phase deviation, the offset angle 26.5° corresponds to the radian 0.462 rad, and the position coordinates are (0.5×cos(0.462), 0.5×sin(0.462))=(0.448 m, 0.223 m). The system records the coordinates and generates a mass adjustment instruction, which is output to the control module to automatically adjust the counterweight to correct the unevenness and ensure that the vibration frequency returns to the threshold range.

[0095] In this embodiment, the dynamic threshold triggering mechanism is realized, the real-time threshold comparison of the frequency data replaces the traditional fixed threshold, and the safety margin is adapted to different rotating speed working conditions; the phase topology denoising technology is realized, the phase distribution matrix is analyzed through the correlation of the time and space dimensions, and the real mass signal and the environmental noise are effectively separated; through the mass distribution probability curve, the traditional discrete point fitting limitation is broken through, and the continuous field quantitative description of the rotor imbalance state is realized.

[0096] In one embodiment, please refer to Figure 4fitting the offset of the rotor by using a least square method based on the initial position coordinates, to obtain a mass deviation coordinate, comprising:

[0097] Step 301, based on the initial position coordinates and a preset coordinate system, the offset of the rotor relative to the center axis is calculated by using the Euclidean distance calculation method, to obtain an offset data set;

[0098] Step 302, if there is an offset in the offset data set that exceeds a preset offset threshold, a median filter method is used to denoise the offset data set, to obtain a smooth offset data set;

[0099] Step 303, based on the smooth offset data set, a least square method is used to fit the offset, to obtain an eccentric vector parameter;

[0100] Step 304, based on the direction and amplitude information in the eccentric vector parameter, a vector decomposition method is used to determine the mass deviation coordinate.

[0101] Based on the initial position coordinates, the calculation of the spatial offset is performed, in the preset rotor three-dimensional coordinate system, the radial offset of each measuring point relative to the theoretical center axis is calculated by using the Euclidean distance calculation model, to generate an offset data set containing the spatial offset vector under multiple rotating speed conditions. Wherein, the offset data set essentially represents the dynamic fluctuation characteristics of the rotor geometric center trajectory. When it is detected that any one of the offset data sets exceeds the preset dynamic offset threshold, the anti-impulse interference mechanism is automatically activated, and the offset data set is denoised by using the median filter algorithm: the spatial offset is sorted and statistically filtered with the rotating speed as the time sequence axis, to effectively suppress the wild point generated by the instantaneous collision of the bearing or electromagnetic interference, and output the smooth offset data set conforming to the rigid body motion law. This process can eliminate a large amount of transient noise interference while retaining the true offset trend.

[0102] Then, based on the smooth data set, a weighted least square method is used for offset trajectory fitting: according to the vibration energy of different rotating speed points, a differentiated weight is given, to construct a continuous function of the offset with respect to the angle. The least square method breaks through the limitation of the traditional average fitting, to generate an eccentric vector parameter containing the direction angle and the amplitude, and the eccentric vector parameter represents the spatial deviation vector of the mass center relative to the rotating axis. Finally, through the vector decomposition method of the polar coordinate, the eccentric vector is decoupled into the mass imbalance components in each balance plane, to output the mass deviation coordinate.

[0103] The embodiment realizes a dynamic threshold self-adaptive system, solves the misjudgment problem of constant threshold under variable working conditions through the characteristics of automatic adjustment of offset threshold with rotating speed, realizes kinematic guidance noise reduction technology, eliminates non-mechanism noise while retaining real offset characteristics through median filtering combined with rigid body motion constraints, realizes energy weighted fitting based on weight distribution strategy of vibration energy, and strengthens the contribution of high speed working condition data. The dynamic accuracy of the eccentricity vector parameter is improved.

[0104] In one embodiment, referring to Figure 5 , the initial counterweight adjustment scheme is generated based on the mass deviation coordinates, the initial counterweight parameters of the initial counterweight adjustment scheme are optimized by using a gradient descent algorithm, and an optimized counterweight adjustment scheme is obtained, comprising:

[0105] Step 401, based on the mass deviation coordinates, a deviation vector is calculated to obtain an initial mass deviation distribution;

[0106] Step 402, based on the initial mass deviation distribution, the counterweight mass and the counterweight position are initialized, the initial counterweight adjustment scheme and the initial counterweight parameters corresponding to the initial counterweight adjustment scheme are determined;

[0107] Step 403, if the error analysis result of the initial counterweight parameters is greater than a preset error threshold, the counterweight mass and the counterweight position of the initial counterweight parameters are iteratively updated by using a gradient descent algorithm to obtain optimized parameters;

[0108] Step 404, based on the optimized parameters, the mass deviation distribution is recalculated to obtain the optimized counterweight adjustment scheme.

[0109] Based on the accurate positioning of the mass deviation coordinates, a deviation vector in a three-dimensional space is first calculated, which integrates the radial offset amplitude, the circumferential angle and the axial position, to generate an initial mass deviation distribution reflecting the unbalance state of the rotor. The initial mass deviation distribution is in polar coordinate form and contains the core area of the mass defect and the gradient diffusion characteristics. Based on the initial mass deviation distribution, intelligent initialization of the counterweight parameters is automatically triggered: according to the rotor dynamics characteristics and the material density constraints, the recommended mass range and the installation angle range of the counterweight block are derived through inverse vector operation to generate an initial counterweight adjustment scheme containing the initial counterweight position and the initial counterweight mass. The initial counterweight position is the installation angle range of the counterweight block, and the initial counterweight mass is the recommended mass range of the counterweight block. The scheme synchronously outputs the initial counterweight parameters of the key performance indicators, which can be the mass tolerance, the phase tolerance and the estimated residual vibration energy value. The initial counterweight parameters can include the initial counterweight position and the initial counterweight mass, or the effectiveness parameters for evaluating the counterweight mass and the counterweight position.

[0110] Then, error analysis is performed based on the initial counterweight parameters to obtain the error analysis results. When the error analysis results show that the predicted residual vibration value exceeds the dynamic error threshold, which is associated with the rotor safety level, the system activates the gradient-driven optimization engine. Starting from the initial parameters, the algorithm iteratively searches along the negative gradient direction of the vibration energy function: by using the mass and angle parameters of the virtual perturbation counterweight, the sensitivity matrix of the objective function of the residual vibration amplitude is calculated, and the parameter update step size is dynamically adjusted. After multiple rounds of intelligent iteration, the optimized parameters that converge the vibration energy to the safe domain are output. Finally, the mass deviation distribution model is reconstructed based on the optimized parameters to generate an engineering-executable optimized counterweight adjustment scheme.

[0111] For example, generating a counterweight adjustment scheme using mass deviation coordinates first involves obtaining the mass deviation coordinates from the input data. Assuming the initial mass deviation coordinates are (x=0.5m, y=0.3m, z=0.2m), these represent the offset of the object's center of mass from its ideal position, with the goal of adjusting the center of mass to the origin (0,0,0). The counterweight mass and position are then optimized using the gradient descent algorithm. The counterweight parameters are initialized, with the initial counterweight mass set to m=1kg and the position coordinates to (x=0.5m, y=0.3m, z=0.2m). c =0.1m, y c =0.1m, z c =0.1m). The objective function is defined as the sum of squares of the centroid offsets. The formula for calculating the objective function E is as follows:

[0112] E=x 2 +y 2 +z 2

[0113] Where (x, y, z) are the initial mass deviation coordinates, and the centroid coordinates are updated by calculating the effect of the counterweight on the centroid. The calculation formula for ) is as follows:

[0114]

[0115]

[0116]

[0117] and Similarly, where m is the initial counterweight mass, and (x, y, z) are the coordinates of the initial counterweight position, m c Let x be the mass deviation value of the initial mass deviation distribution. c y c , z c Let m be the initial mass deviation distribution and its positional deviation value, assumed to be 10 kg. The gradient descent algorithm iteratively updates the weight parameters with a learning rate α = 0.01, calculating the objective function with respect to m.c , x c , y c , z c The partial derivative of E. Assuming the initial E = 0.38, after 10 iterations, E is reduced to 0.05, and the counterweight parameters converge to m c = 1.2 kg, x c = 0.08 m, y c = 0.06 m, and z c = 0.04 m. The analysis process verifies that the counterweight position is close to the opposite direction of the deviation, and the mass is slightly increased to balance the deviation. The final output counterweight scheme is to add 1.2 kg of counterweight at (0.08 m, 0.06 m, 0.04 m), and the centroid deviation is reduced to 0.05, meeting the accuracy requirement. If the deviation is still above the threshold, the number of iterations can be increased or the learning rate can be adjusted.

[0118] In this embodiment, the vectorization solving technology is realized, the three-dimensional deviation vector breaks through the limitation of traditional plane projection, and the axial asymmetric imbalance is accurately captured; the dynamic guidance initialization is realized, the counterweight parameter initialization is fused with the rotor modal shape data to avoid resonance risk; the gradient descent algorithm based on vibration energy sensitivity is iteratively updated, which makes the optimization efficiency several times higher than that of traditional methods.

[0119] In one embodiment, referring to Figure 6 , the counterweight parameters based on the optimized counterweight adjustment scheme are simulated in a simulated environment to obtain a simulation vibration signal, including:

[0120] Step 501, loading the initial counterweight parameters in the simulated environment, performing dynamic response simulation to obtain vibration signal data;

[0121] Step 502, based on the vibration signal data, using signal extraction technology to extract its vibration characteristics to obtain vibration characteristic parameters;

[0122] Step 503, if the vibration characteristic parameters exceed the preset balance threshold, adjusting the counterweight parameters of the optimized counterweight adjustment scheme through the gradient descent algorithm to generate new counterweight parameters;

[0123] Step 504, based on the new counterweight parameters, re-performing dynamic response simulation in the simulation environment to obtain updated vibration signals;

[0124] Step 505, based on the updated vibration signals, using signal processing technology to extract new vibration characteristics to determine the simulation vibration signal.

[0125] After obtaining the initial counterweight parameters, they are imported into a multi-physics coupled simulation environment, which can be a finite element model based on the rotor, bearing, and shell system, which can accurately simulate the dynamic behavior of the rotor after the counterweight is applied. Through full-speed transient simulation, high-fidelity vibration signal data is output. Based on the vibration signal data, signal extraction techniques are used to extract key vibration characteristics to obtain vibration characteristic parameters. For example, background noise can be stripped through wavelet packet decomposition, and modulation sidebands can be demodulated through Hilbert transform to condense vibration characteristic parameters including fundamental frequency amplitude, frequency multiplication energy ratio, phase coherence, etc. The signal extraction technique can be an adaptive signal deconstruction technique.

[0126] When the vibration characteristic parameters exceed the dynamic balance threshold, gradient-driven re-optimization is started, taking the current counterweight parameters as the initial point, calculating the partial derivative matrix of the vibration energy function with respect to the counterweight mass and angle through the gradient descent algorithm, and adaptively adjusting the parameter step size in the negative gradient direction. After each iteration generates a new counterweight parameter, the simulation environment is triggered to run again, forming a closed loop of parameter updating and simulation verification, and finally obtaining a simulation vibration signal that meets the balance standard.

[0127] For example, in the simulation environment, dynamic response simulation is performed on the preliminary counterweight parameters. First, a virtual model is constructed, assuming a rotating machinery rotor system with a mass of 10 kg, a speed of 1500 rpm, and an initial eccentric counterweight of 0.1 kg located at a radius of 0.05 m. A multi-body dynamics software is used to establish the rotor model, set the material properties to steel (density 7850 kg / m³), and apply rotational constraints. The dynamic response simulation uses the Runge-Kutta algorithm to solve the motion equation, with a time step of 0.001 s and a simulation duration of 2 s, calculating the vibration displacement of the rotor under different counterweights. The vibration signal is obtained through virtual acceleration sensors, with a sensor sampling frequency of 1000 Hz, outputting a vibration acceleration time series, and assuming a peak acceleration of 0.5 m / s². Signal processing uses the Fast Fourier Transform to convert time-domain signals to frequency-domain, extracting the main frequency component (25 Hz, corresponding to the speed). Analyzing the vibration amplitude, if the main frequency amplitude exceeds the threshold of 0.3 m / s², adjust the counterweight. The optimization algorithm uses a genetic algorithm with an initial population size of 50 and 20 iterations, with the objective function being to minimize the main frequency amplitude, adjusting the counterweight mass to 0.12 kg and the position angle to 15°. After re-simulation, the peak acceleration of the new vibration signal is reduced to 0.25 m / s². When judging the balance threshold, compare the main frequency amplitude with 0.3 m / s², if less than or equal to the threshold, it is determined to meet the balance requirements. The final result shows that the adjusted amplitude is 0.25 m / s², meeting the requirements.

[0128] The embodiment realizes intelligent signal decoupling technology, breaks through the limitations of traditional algorithms in adaptive signal decomposition, and accurately extracts weak fault characteristics in a strong noise background. Closed-loop gradient optimization is realized, and through the combination of simulation and optimization process, the real-time linkage mechanism reduces the time consumption of single iteration, and the efficiency is improved several times compared with traditional offline optimization.

[0129] In one embodiment, referring to Figure 7 , if the simulated vibration signal exceeds the balance threshold, a particle swarm optimization algorithm is used to re-iteratively update the weight parameters of the optimized counterweight adjustment scheme to obtain a target counterweight scheme, including:

[0130] Step 601, based on the simulated vibration signal, Fourier transform is used to perform frequency domain decomposition to obtain frequency domain vibration characteristics;

[0131] Step 602, if the amplitude of the frequency domain vibration characteristics exceeds the balance threshold, a signal processing algorithm is used to denoise the frequency domain vibration characteristics to obtain smooth vibration characteristics;

[0132] Step 603, based on the smooth vibration characteristics, the particle swarm optimization algorithm is used to re-iteratively update the weight parameters of the optimized counterweight adjustment scheme to generate the target counterweight scheme.

[0133] The vibration signal obtained in the simulation environment is first subjected to high-resolution Fourier transform for frequency domain decomposition, which can suppress spectral leakage, accurately separate the fundamental frequency, harmonics and subsynchronous components, and generate frequency domain vibration characteristics containing amplitude, frequency and phase. The frequency domain vibration characteristics quantify the residual vibration energy distribution of the counterweighted rotor, meeting the analysis requirements of ultra-high speed rotors. When the amplitude of the frequency domain vibration characteristics exceeds the dynamic balance threshold, the intelligent frequency domain noise reduction channel is activated, and a signal processing algorithm is used to denoise the frequency domain vibration characteristics. On the premise of retaining the main vibration energy, the non-mechanism components such as electromagnetic interference and background noise are eliminated, and the smooth vibration characteristics conforming to the rigid body dynamics law are output. The signal processing algorithm can be adaptive wavelet threshold filtering and coherent averaging technology.

[0134] Based on the smooth vibration characteristics, the particle swarm optimization engine is called, the weight mass and angle parameters are mapped to the position vector of the particle swarm, the residual vibration energy is taken as the fitness function, the weight parameters of the optimized counterweight adjustment scheme are iteratively updated, and the particle swarm is distributed in the parameter space through the group cooperation mechanism: individual particles remember the historical optimal solution, global particles share optimal position information, and combined with the adaptive adjustment strategy of inertia weight, efficient global optimization is realized, and the target counterweight scheme that minimizes the vibration energy is output.

[0135] For example, to realize vibration signal simulation and optimize the counterweight parameters, first, the vibration signal is collected by the sensor, assuming that the collected signal frequency is 50 Hz, the amplitude is 0.02 mm, and the threshold is set to 0.015 mm. The simulation system establishes a rotor model by using a finite element analysis software, the model contains four counterweight points, the initial counterweight mass of each point is 0.5 kg, and the initial phase angle is 0°. After running the simulation, the vibration amplitude is calculated to be 0.018 mm, which exceeds the threshold 0.015 mm, triggering the optimization process. The system automatically calls the particle swarm optimization algorithm, sets the particle swarm size to 30, the maximum iteration number to 100, the inertia weight w to linearly decrease from 0.9 to 0.4, and sets the learning factor c1=c2=2. The position of each particle represents a set of counterweight parameters, including mass and phase angle, and the search space limits the mass to 0.1-1.0 kg and the phase angle to 0-360°. The particle swarm optimization algorithm updates the particle velocity and position by iteration, and calculates the objective function, i.e., the square of the difference between the vibration amplitude and the threshold. For example, at the 68th iteration, a set of optimized solutions is found: counterweight point 1: mass 0.62 kg, phase angle 45°, counterweight point 2: mass 0.55 kg, phase angle 120°, counterweight point 3: mass 0.48 kg, phase angle 200°, and counterweight point 4: mass 0.51 kg, phase angle 300°. Inputting this scheme into the simulation model, the vibration amplitude is recalculated to be 0.013 mm, which is lower than the threshold 0.015 mm, meeting the requirements.

[0136] In the embodiment, the dynamic guidance noise reduction mechanism is realized, the adaptive filtering based on the rotor motion equation effectively retains the frequency band strongly related to the mass defect; the global optimization of swarm intelligence is realized, the particle swarm optimization algorithm breaks through the local convergence limitation of gradient optimization, so that the residual vibration is further reduced than the gradient method; and the cross-dimension parameter mapping is realized, the intelligent mapping mechanism of the vibration characteristics to the counterweight parameters can reduce the number of optimization iterations.

[0137] The air compressor rotor testing device provided by the application is described below, and the air compressor rotor testing device described below can be correspondingly referred to the air compressor rotor testing method described above.

[0138] The application further provides an air compressor rotor testing device, comprising:

[0139] The acquisition module is configured to acquire vibration signal data of the rotor at multiple rotation speeds, and analyze the vibration signal data by using a fast Fourier transform algorithm to obtain vibration frequencies and phase distribution.

[0140] The analysis module is configured to perform weighted analysis on the phase distribution to determine initial position coordinates of the mass distribution unevenness if the vibration frequencies exceed the preset frequency threshold.

[0141] a fitting module configured to fit the offset of the rotor based on the initial position coordinates to obtain quality deviation coordinates by using a least square method;

[0142] an optimization module configured to generate an initial counterweight adjustment scheme based on the quality deviation coordinates, and to optimize initial counterweight parameters of the initial counterweight adjustment scheme by using a gradient descent algorithm to obtain an optimized counterweight adjustment scheme;

[0143] a simulation module configured to perform dynamic response simulation on the optimized counterweight adjustment scheme in a simulation environment based on counterweight parameters of the optimized counterweight adjustment scheme to obtain a simulation vibration signal;

[0144] an updating module configured to, if the simulation vibration signal exceeds a balance threshold, update the counterweight parameters of the optimized counterweight adjustment scheme by using a particle swarm optimization algorithm to obtain a target counterweight scheme;

[0145] The target counterweight scheme is used to be applied to the rotor for testing, so that the balance state of the rotor reaches a set standard.

[0146] Finally, it should be noted that: the above examples are only used to illustrate the technical solutions of the present application, and not to limit them; although the present application has been described in detail with reference to the foregoing examples, those skilled in the art should understand that: it can still modify the technical solutions recorded in the foregoing examples, or make equivalent replacement for part of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. An air compressor rotor testing method, characterized by, Computer-executed, comprising: Obtaining vibration signal data of the rotor at multiple rotation speeds, using fast Fourier transform algorithm to analyze the vibration signal data, and obtaining vibration frequency and phase distribution; If the vibration frequency exceeds a preset frequency threshold, performing weighted analysis on the phase distribution to determine the initial position coordinates of the uneven mass distribution; Based on the initial position coordinates, using the least square method to fit the offset of the rotor to obtain the mass deviation coordinates; Based on the mass deviation coordinates, generating an initial counterweight adjustment scheme, using the gradient descent algorithm to optimize the initial counterweight parameters of the initial counterweight adjustment scheme to obtain an optimized counterweight adjustment scheme; Based on the counterweight parameters of the optimized counterweight adjustment scheme, performing dynamic response simulation in a simulation environment to obtain simulation vibration signals; If the simulation vibration signals exceed a balance threshold, using a particle swarm optimization algorithm to re-iterate and update the counterweight parameters of the optimized counterweight adjustment scheme to obtain a target counterweight scheme; Wherein, the target counterweight scheme is used to be applied to the rotor for testing, so that the balance state of the rotor reaches the set standard; Wherein, if the vibration frequency exceeds a preset frequency threshold, the vibration signal data of the rotor is obtained, and the fast Fourier transform algorithm is used to calculate the vibration frequency value of the vibration signal data to obtain frequency data; If the frequency value of the frequency data exceeds the preset frequency threshold, based on the phase distribution, a phase distribution matrix is generated; Based on the phase distribution matrix, using a weighted analysis algorithm to calculate the weighted phase value of the phase distribution matrix to determine the phase distribution characteristics; Comparing the phase distribution characteristics with a preset mass distribution model, using the least square method algorithm to fit the mass distribution curve of the unbalanced mass of the rotor on the balance surface to determine the uneven degree parameter, wherein the uneven degree parameter is an evaluation index of the unbalanced state of the rotor; Based on the uneven degree parameter, the spatial deviation of the mass distribution is calculated to determine the initial position coordinates; Wherein, based on the mass deviation coordinates, an initial counterweight adjustment scheme is generated, the gradient descent algorithm is used to optimize the initial counterweight parameters of the initial counterweight adjustment scheme to obtain an optimized counterweight adjustment scheme, comprising: Based on the mass deviation coordinates, a deviation vector is calculated to obtain an initial mass deviation distribution; Based on the initial mass deviation distribution, the counterweight mass and the counterweight position are initialized to determine the initial counterweight adjustment scheme and the initial counterweight parameters corresponding to the initial counterweight adjustment scheme; If the error analysis result of the initial counterweight parameters is greater than a preset error threshold, the counterweight mass and the counterweight position of the initial counterweight parameters are iteratively updated by the gradient descent algorithm to obtain optimized parameters; Based on the optimized parameters, the mass deviation distribution is recalculated to obtain the optimized counterweight adjustment scheme. Further comprising:

2. The air compressor rotor testing method of claim 1, wherein, Applying the target counterweight scheme to the rotor through an automatic execution mechanism to obtain real-time vibration feedback signals; ​ If the vibration feedback signal contains residual vibration, the vibration feedback signal is analyzed again, the mass deviation coordinates are updated, and the feedback balance weight parameters are determined; Based on the feedback balance weight parameters, continuous iterative optimization and real-time feedback adjustment are performed to generate a dynamic balance weight scheme, wherein the working state of the rotor reaches the set standard when the dynamic balance weight scheme is applied to the rotor.

3. The air compressor rotor testing method of claim 1, wherein, The initial position coordinates are used to fit the rotor offset using the least squares method to obtain the mass deviation coordinates, including: Based on the initial position coordinates and the preset coordinate system, the Euclidean distance calculation method is used to calculate the offset of the rotor relative to the center axis to obtain the offset data set; If the offset in the offset data set exceeds the preset offset threshold, the median filter method is used to denoise the offset data set to obtain a smooth offset data set; Based on the smooth offset data set, the least squares method is used to fit the offset to obtain the eccentric vector parameters; Based on the direction and amplitude information in the eccentric vector parameters, the vector decomposition method is used to determine the mass deviation coordinates.

4. The air compressor rotor testing method of claim 1, wherein, The initial balance weight parameters are loaded in the simulation environment, and dynamic response simulation is performed to obtain vibration signal data; Based on the vibration signal data, signal extraction technology is used to extract its vibration characteristics to obtain vibration characteristic parameters; If the vibration characteristic parameters exceed the preset balance threshold, the gradient descent algorithm is used to adjust the balance weight parameters of the optimized balance weight adjustment scheme to generate new balance weight parameters; Based on the new balance weight parameters, dynamic response simulation is performed again in the simulation environment to obtain updated vibration signals; Based on the updated vibration signals, signal processing technology is used to extract new vibration characteristics to determine the simulation vibration signals. If the simulation vibration signals exceed the balance threshold, the particle swarm optimization algorithm is used to iteratively update the balance weight parameters of the optimized balance weight adjustment scheme to obtain a target balance weight scheme, including:

5. The air compressor rotor testing method of claim 1, wherein, Based on the simulation vibration signals, Fourier transform is used to perform frequency domain decomposition to obtain frequency domain vibration features; If the amplitude of the frequency domain vibration features exceeds the balance threshold, signal processing algorithms are used to denoise the frequency domain vibration features to obtain smooth vibration features; Based on the smooth vibration features, the particle swarm optimization algorithm is used to iteratively update the balance weight parameters of the optimized balance weight adjustment scheme to generate the target balance weight scheme. The acquisition module is configured to acquire vibration signal data of a rotor at multiple rotation speeds, and analyze the vibration signal data using a fast Fourier transform algorithm to obtain vibration frequency and phase distribution; 6. An air compressor rotor testing device, characterized by, The analysis module is configured to analyze the phase distribution using a weighted analysis method if the vibration frequency exceeds a preset frequency threshold to determine initial position coordinates of mass distribution unevenness; The fitting module is configured to fit the rotor offset using the least squares method based on the initial position coordinates to obtain the mass deviation coordinates; ​ ​ An optimization module is configured to generate an initial counterweight adjustment scheme based on the mass deviation coordinates, optimize initial counterweight parameters of the initial counterweight adjustment scheme by using a gradient descent algorithm, and obtain an optimized counterweight adjustment scheme; An emulation module is configured to perform dynamic response emulation on the optimized counterweight adjustment scheme in a simulation environment based on counterweight parameters of the optimized counterweight adjustment scheme, and obtain an emulation vibration signal; An updating module is configured to, if the emulation vibration signal exceeds a balance threshold, update the counterweight parameters of the optimized counterweight adjustment scheme by using a particle swarm optimization algorithm, and obtain a target counterweight scheme; The target counterweight scheme is used to be applied to the rotor for testing, so that a balance state of the rotor reaches a set standard. The analysis module is further configured to: If the vibration frequency exceeds a preset frequency threshold, obtain vibration signal data of the rotor, and calculate a vibration frequency value of the vibration signal data by using a fast Fourier transform algorithm to obtain frequency data; If a frequency value of the frequency data exceeds the preset frequency threshold, generate a phase distribution matrix based on the phase distribution; Calculate a weighted phase value of the phase distribution matrix by using a weighted analysis algorithm based on the phase distribution matrix to determine a phase distribution feature; Compare the phase distribution feature with a preset mass distribution model, fit a mass distribution curve of unbalanced mass of the rotor on a balance plane by using a least square method algorithm to determine an uneven degree parameter, wherein the uneven degree parameter is an evaluation index of the unbalanced state of the rotor; Calculate a spatial deviation of the mass distribution based on the uneven degree parameter to determine the initial position coordinates. The optimization module is further configured to: Calculate a deviation vector based on the mass deviation coordinates to obtain an initial mass deviation distribution; Initialize counterweight mass and counterweight position based on the initial mass deviation distribution to determine the initial counterweight adjustment scheme and initial counterweight parameters corresponding to the initial counterweight adjustment scheme; If an error analysis result of the initial counterweight parameters is greater than a preset error threshold, update the counterweight mass and the counterweight position of the initial counterweight parameters by using a gradient descent algorithm to obtain optimized parameters; Recalculate the mass deviation distribution based on the optimized parameters to obtain the optimized counterweight adjustment scheme.

Images