Dynamic balance evaluation method for impeller of axial flow fan based on machine vision

Abstract

The invention relates to the technical field of image processing, and provides an axial flow fan impeller dynamic balance evaluation method based on machine vision, which comprises the following steps: collecting continuous frames of impeller images of an axial flow fan rotating at a high speed, obtaining analysis time periods and each frame of impeller edge image corresponding to a plurality of moments therein, and extracting a plurality of key points from the impeller edge images; obtaining impeller load non-uniformity of the analysis time period; obtaining a dynamic non-stability index of the analysis time period; obtaining the dynamic balance deviation of the impeller in the analysis time period; obtaining the axial deflection index of the impeller in the analysis time period; obtaining an impeller structure anomaly index of the analysis time period; obtaining a visual fusion dynamic balance index of the impeller in the analysis time period; and obtaining an adjustment dynamic balance threshold value of the analysis time period and carrying out dynamic balance evaluation on the impeller. The invention aims to solve the problem that accurate dynamic balance evaluation is difficult to perform through trajectory analysis due to image blurring caused by high-speed rotation of an impeller.

Description

Technical Field

[0001] The present invention relates to the technical field of image processing, and in particular to a method for evaluating the dynamic balance of an axial flow fan impeller based on machine vision. Background Art

[0002] Axial flow fans are widely used in industrial scenarios such as mines, tunnels, subways, electric power, and petrochemicals. They are key gas transportation and ventilation equipment. The impeller is the core component of the axial flow fan, and its dynamic balance directly affects the vibration level, service life, energy efficiency level, and operational safety of the entire machine. An impeller with poor dynamic balance may cause equipment damage or loose foundation, and long-term eccentric operation will cause premature bearing fatigue and shorten the life of the fan. Therefore, efficient, accurate, and real-time dynamic balance assessment of axial flow fan impellers is an important means to ensure the reliability of ventilation systems, extend equipment service life, and reduce operation and maintenance costs. In recent years, with the development of machine vision technology, especially the maturity of high-speed image acquisition, image registration, three-dimensional reconstruction, and intelligent image analysis algorithms, non-contact dynamic balance assessment methods based on machine vision have gradually become a research hotspot.

[0003] The advantage of machine vision in dynamic balancing detection lies in non-contact measurement, which does not affect the normal operation of the fan, and image recognition can achieve high-precision rotation state capture and tiny eccentricity detection, and can be deployed on the production line to achieve continuous monitoring and closed-loop control. However, in a high-speed rotation environment, it is difficult to stably extract the trajectory information of key feature points during the impeller rotation process. Since the high-speed rotation of the impeller will cause image blur, feature drift, trajectory breakage and other problems, traditional image acquisition and trajectory analysis algorithms are difficult to obtain a representative rotation path within a limited time window, which in turn affects the accuracy of dynamic balancing assessment. In addition, on-site factors such as uneven lighting, background interference, and feature occlusion will also interfere with the interpretation of visual images, resulting in misjudgment or missed judgment. Summary of the Invention

[0004] The present invention provides a method for evaluating the dynamic balance of an axial flow fan impeller based on machine vision to solve the problem that the high-speed rotation of the impeller causes image blur and makes it difficult to accurately evaluate the dynamic balance through trajectory analysis. The technical solution adopted is as follows: The present invention proposes a method for evaluating the dynamic balance of an axial flow fan impeller based on machine vision, which includes the following steps: The system collects continuous frames of impeller images of a high-speed rotating axial flow fan, obtains impeller edge images of each frame corresponding to the analysis period and several moments therein, extracts several key points from the impeller edge images, and records parameter data of several key operating conditions of the axial flow fan at each moment and the temperature of several locations in the impeller. Based on the smooth performance of the trajectories of key points in the impeller edge images of consecutive frames during the analysis period, and the area distribution of the closed areas formed by the trajectories, the impeller load unevenness during the analysis period is obtained. The dynamic instability index during the analysis period is obtained by combining the changes in the area differences of different blades in the impeller edge images of consecutive frames. Based on the changes in the dynamic instability index of adjacent time periods, the differences in the temperature difference trends at different positions of the impeller, and the changes in the fluctuations of the parameter data of each key working condition, the impeller dynamic balance deviation during the analysis period is obtained. The impeller axial deflection index for the analysis period is obtained based on the position change of the center of mass and the diameter change of the trajectory area formed by the trajectory of key points in the impeller edge images of consecutive frames in the analysis period. The impeller structural anomaly index for the analysis period is obtained by combining the grayscale expression changes of each blade area in the impeller images of adjacent frames. The visual fusion dynamic balance index of the impeller for the analysis period is obtained based on the impeller dynamic balance deviation and the impeller structural anomaly index. The initial dynamic balance threshold of the impeller is adjusted based on the visual fusion dynamic balance index, the adjusted dynamic balance threshold of the analysis period is obtained, and the dynamic balance evaluation of the impeller is performed.

[0005] Optionally, the obtaining of the impeller load non-uniformity during the analysis period includes the following specific methods: Fit the position of any key point in the impeller edge image of each frame during the analysis period to obtain the motion trajectory of the key point during the analysis period, and obtain the closed area formed by closing the motion trajectory; divide the closed area into a left area and a right area by a vertical line passing through the center point of the impeller, and obtain the absolute value of the area difference between the left area and the right area as the closed area difference of the key point during the analysis period; Obtaining the direction from the previous position of the key point to the next position in the impeller edge image of any adjacent frames in the analysis period as the movement direction of the key point in the previous frame of the adjacent frames in the analysis period; obtaining the movement direction of the key point in each frame in the analysis period, and multiplying the standard deviation of the angles of the movement directions of the key point in all adjacent frames in the analysis period by the closed area difference as the trajectory nonuniformity of the key point in the analysis period; The mean value of the trajectory unevenness of all key points during the analysis period is taken as the impeller load unevenness during the analysis period.

[0006] Optionally, the obtaining of the dynamic instability index during the analysis period includes the following specific methods: For any impeller edge image frame in the analysis period, obtain several blade regions in the impeller edge image frame, and obtain the area of ​​each blade region, obtain the absolute value of the difference between the areas of any two blade regions, and take the average of the absolute values ​​of the difference between the areas of all two blade regions in the impeller edge image frame as the blade area difference factor of the impeller edge image frame; The absolute value of the difference between the blade area difference factors of any adjacent frame impeller edge images in the analysis period is obtained, and the average of the absolute values ​​of the difference between the blade area difference factors of all adjacent frame impeller edge images in the analysis period is multiplied by the impeller load non-uniformity in the analysis period as the dynamic instability index of the analysis period.

[0007] Optionally, the obtaining of the impeller dynamic balance deviation during the analysis period includes the following specific methods: Based on the changes in the dynamic instability index in adjacent periods and the differences in the temperature difference change trends at different impeller positions, the impeller load trend index of the analysis period is obtained; Obtain the standard deviation of all parameter data of any key operating condition in the analysis period, obtain the standard deviation of all parameter data of the key operating condition in the immediately preceding period of the analysis period, and use the ratio of the standard deviation corresponding to the key operating condition in the analysis period to the standard deviation corresponding to the key operating condition in the immediately preceding period as the parameter fluctuation change factor for the key operating condition in the analysis period; Based on the impeller load trend index of the analysis period and the mean value of the parameter fluctuation change factors of each key working condition during the analysis period, the impeller dynamic balance deviation of the analysis period is obtained. The impeller dynamic balance deviation is positively correlated with the impeller load trend index, and negatively correlated with the mean value of the parameter fluctuation change factors of each key working condition.

[0008] Optionally, the obtaining of the impeller load trend index during the analysis period includes the following specific methods: For the temperatures of several positions in the impeller at any moment in the analysis period, the absolute value of the difference between the temperatures of any two positions is obtained, and the average of the absolute values ​​of the temperature differences of all two positions in the impeller at that moment is used as the average temperature difference at that moment; a coordinate system is constructed with time as the horizontal axis and temperature difference as the vertical axis, the average temperature difference at each moment in the analysis period is mapped to the coordinate system to obtain several data points, and the data points are fitted by the least squares method to obtain a fitting line and its slope, and the slope is used as the temperature difference change factor of the analysis period; The ratio of the temperature difference change factor of the analysis period to the temperature difference change factor of the adjacent previous period is obtained, the ratio of the dynamic instability index of the analysis period to the dynamic instability index of the adjacent previous period is obtained, and the product of the two ratios is used as the impeller load trend index of the analysis period.

[0009] Optionally, the impeller axial deflection index during the analysis period is obtained by: For the position of any key point in each impeller edge image frame during the analysis period, the positions of the key point in the impeller edge images of adjacent frames are connected to obtain the movement trajectory of the key point during the analysis period. The movement trajectory forms several closed areas, which are recorded as several trajectory areas. The center of mass of each trajectory area and the length of the horizontal straight line passing through the center of mass in the trajectory area are obtained as the horizontal diameter of each trajectory area; Based on the distribution of centroids and changes in horizontal diameters in the trajectory area of ​​key points, the axial deflection coefficients of each key point during the analysis period are obtained; The average value of the axial deflection coefficients of all key points during the analysis period is taken as the impeller axial deflection index during the analysis period.

[0010] Optionally, the axial deflection coefficient of each key point during the analysis period is obtained by: For several trajectory areas of any key point in the analysis period, the distance between the centroids of any two trajectory areas is obtained, and the horizontal diameters of all trajectory areas of the key point are arranged in ascending order to obtain the horizontal diameter sequence of the key point. The ratio of the latter horizontal diameter to the previous horizontal diameter of two adjacent horizontal diameters in the horizontal diameter sequence is obtained, and the mean of the ratios corresponding to all adjacent horizontal diameters in the horizontal diameter sequence is multiplied by the standard deviation of the distances between the centroids of all pairwise trajectory areas of the key point as the axial deflection coefficient of the key point in the analysis period.

[0011] Optionally, the obtaining of the impeller structure abnormality index during the analysis period includes the following specific methods: For any impeller image frame in the analysis period, the number of blade areas in the impeller image frame and the average of the grayscale values ​​of the pixels in each blade area are obtained, and the product of the number of blade areas and the average of the grayscale values ​​is used as the grayscale visual representation value of the impeller image frame; the absolute value of the difference between the grayscale visual representation values ​​of any adjacent impeller image frames in the analysis period is obtained; Based on the impeller axial deflection index of the analysis period and the average of the absolute values ​​of the difference in grayscale visual appearance values ​​of all adjacent frame impeller images in the analysis period, the impeller structure anomaly index of the analysis period is obtained. The impeller structure anomaly index is positively correlated with the impeller axial deflection index, and negatively correlated with the average of the absolute values ​​of the difference in grayscale visual appearance values.

[0012] Optionally, the obtaining of the visual fusion dynamic balance index of the impeller during the analysis period includes the following specific methods: The sum of the inverse proportional normalized result of the impeller dynamic balance deviation during the analysis period and the inverse proportional normalized result of the impeller structural abnormality index during the analysis period is used as the visual fusion dynamic balance index of the impeller during the analysis period.

[0013] Optionally, the method of obtaining the adjusted dynamic balance threshold value during the analysis period includes: The product of the initial dynamic balance threshold of the impeller and the visual fusion dynamic balance index of the impeller during the analysis period is used as the adjusted dynamic balance threshold during the analysis period.

[0014] The beneficial effects of the present invention are as follows: the present invention uses a high-speed camera to capture continuous frames of impeller images, analyzes the trajectory symmetry and edge smoothness of key points during the impeller rotation process to quantify the impeller load unevenness, and combines the area change of the blade area to obtain a dynamic instability index, which reflects the dynamic disturbance amplitude caused by the load unevenness during the rotation of the axial flow fan impeller; and by analyzing the impeller surface temperature difference change trend and the change of the dynamic instability index in adjacent time periods, obtains an impeller load trend index to quantify the dynamic stability degradation caused by the influence of temperature change on the material, and then combines the fluctuation of key operating parameter data to eliminate the influence of other operating parameters and clarify the impeller dynamic balance deviation; then, the structural anomaly index of the fan impeller in the rotating state is explained by the axial offset of the key point trajectory during the rotation process and the sampling error of machine vision, and the visual fusion dynamic balance index is obtained in combination with the dynamic balance deviation. By combining the two-dimensional features and the three-dimensional features obtained by reasoning, the initial dynamic balance threshold is adjusted to achieve dynamic adjustment of the dynamic balance assessment mechanism of the axial flow fan impeller, effectively helping relevant personnel make more accurate decisions after the dynamic balance assessment and ensuring the safety and stability of the equipment under various conditions. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0016] Figure 1 A schematic flow chart of a method for evaluating the dynamic balance of an axial flow fan impeller based on machine vision according to one embodiment of the present invention; Figure 2 Schematic diagram of the edge image of the axial flow fan impeller. DETAILED DESCRIPTION

[0017] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0018] See also Figure 1 , which shows a flow chart of a method for evaluating the dynamic balance of an axial flow fan impeller based on machine vision according to an embodiment of the present invention. The method comprises the following steps: Step S001: Collect continuous frames of impeller images of a high-speed rotating axial flow fan, obtain the impeller edge images of each frame corresponding to the analysis period and several moments therein, extract several key points from the impeller edge images; record the parameter data of several key working conditions of the axial flow fan at each moment and the temperatures of several positions in the impeller.

[0019] The purpose of this embodiment is to use a high-speed camera to capture video stream images of the impeller rotation process of an axial flow fan, and to achieve a visual fusion dynamic balance state of the impeller over a period of time by analyzing the dynamic balance and axial deflection of the impeller. At the same time, the influence of the temperature change of the fan impeller and the parameter changes of several key working conditions of the fan on the impeller rotation process is considered, so as to dynamically adjust the dynamic balance threshold to realize the dynamic balance evaluation of the impeller rotation process.

[0020] Specifically, a high-speed industrial camera is installed at the visual window or inspection port of the axial flow fan impeller housing. The camera should have low exposure delay and shutter synchronization capabilities to ensure that it can capture clear images of the impeller when it rotates at high speed; the impeller image is collected in the form of video stream at a sampling frequency of 10 frames per second, and the collected images are pre-processed to obtain continuous frame impeller images. The impeller edge image is obtained by using the Canny edge detection algorithm for each frame of the impeller image, such as Figure 2 As shown; a preset time window, the time window of this embodiment is described as 5 minutes, and the time window is used to divide the several moments of the collected impeller image into several time periods, and the latest 5 minutes is used as the analysis period for subsequent processing; at the same time, an encoder or photoelectric trigger is installed at the fan shaft end or the motor output shaft position to synchronously collect the starting angle of each rotation circle, which is beneficial to the angle alignment of subsequent image frames and the realization of periodic state analysis. All collected images are temporarily stored in the cache for synchronous calibration, and the pulse signal of the photoelectric encoder or Hall sensor is connected to the acquisition system to establish a mapping relationship between the image frame-angle time, so as to determine the mapping relationship between the impeller image and the moment.

[0021] Furthermore, for any frame of the impeller edge image, several key points are marked at the blade tip, blade root and central axis positions respectively. In this embodiment, a key point is marked for the blade tip, blade root and central axis positions corresponding to each blade respectively, and in other frame impeller edge images, the key points at the corresponding positions are marked according to the position changes of the key points in the continuous frame images, thereby obtaining several key points and their positions in the continuous frame impeller edge images.

[0022] Furthermore, a high-speed infrared camera is arranged to obtain infrared images of the fan impeller, and the sampling frequency is set to once per second. The temperatures of the impeller at the tip, root and center axis at each moment are obtained based on the infrared images; at the same time, parameter data of several key working conditions are obtained at the same sampling frequency. The key working conditions include speed, flow rate, etc., and the parameter data of several key working conditions of the axial flow fan at each moment and the temperatures of several positions in the impeller are obtained.

[0023] It should be noted that by analyzing the spatial path changes of the impeller edge and time transformation, signs of dynamic imbalance such as jitter, eccentricity, and swing can be detected. The spatial path of the edge point has high temporal resolution and sub-pixel accuracy, which is suitable for detecting small deviations. Compared with the traditional method of analyzing the overall image, it has a certain degree of reliability.

[0024] Step S002: Based on the trajectory smoothing performance of key points in the impeller edge images of continuous frames in the analysis period and the area distribution of the closed area formed by the trajectory, the impeller load unevenness of the analysis period is obtained; combined with the changes in the area differences of different blades in the impeller edge images of continuous frames, the dynamic instability index of the analysis period is obtained; based on the changes in the dynamic instability index of adjacent time periods and the differences between the temperature difference change trends at different positions of the impeller, combined with the changes in the fluctuation of the parameter data of each key working condition, the impeller dynamic balance deviation of the analysis period is obtained.

[0025] It should be noted that when the fan impeller is rotating, the motion trajectory of the key point is a closed area, and under normal circumstances, the closed area should be symmetrical and circular. The uneven load of the impeller is reflected by performing left-right symmetry analysis on the closed area. At the same time, the change in the direction of the trajectory reflects whether its overall motion trajectory is smooth. The more severe the fluctuation, the more irregular the motion trajectory is and the less it is similar to a circle, which can also reflect the uneven load of the impeller.

[0026] Preferably, in one embodiment of the present invention, the impeller load non-uniformity during the analysis period is obtained based on the smooth trajectory representation of key points in the impeller edge images of consecutive frames during the analysis period and the area distribution of the closed area formed by the trajectory, including the specific method of: The position of any key point in the impeller edge image of each frame in the analysis period is fitted to obtain the motion trajectory of the key point in the analysis period, and the closed area formed by the closed motion trajectory is obtained; the closed area is divided into a left area and a right area by a vertical line passing through the center point of the impeller, and the absolute value of the area difference between the left area and the right area is obtained as the closed area difference of the key point in the analysis period; the direction from the previous position to the next position of the key point in any adjacent frame of the impeller edge image in the analysis period is obtained as the motion direction of the key point in the previous frame of the adjacent frame in the analysis period; the motion direction of the key point in each frame in the analysis period is obtained (the motion direction is not obtained for the last frame in the analysis period), and the standard deviation of the angles of the motion directions of the key point in all adjacent frames in the analysis period, multiplied by the closed area difference, is used as the trajectory unevenness of the key point in the analysis period; the mean of the trajectory unevenness of all key points in the analysis period is used as the impeller load unevenness of the analysis period.

[0027] It should be noted that the greater the difference in closed area, the greater the difference in area between the left and right sides, the less symmetrical the closed area is, and the more uneven the load on the impeller is. At the same time, the standard deviation of the angle between adjacent movement directions reflects the changing fluctuations in the movement direction. The larger the standard deviation, the less the motion trajectory conforms to the expected smooth circular area characteristics of the key points. By taking the average of all key points, the larger the mean, the more it indicates that the edge points have formed an asymmetric trajectory in the moving trajectory, which means that there is serious eccentricity or uneven load on the fan impeller during rotation, and the greater the unevenness of the impeller load.

[0028] It should be further explained that the load unevenness of the impeller during the analysis period refers to the possible offset of the force center of the impeller during rotation, such as mechanical eccentricity caused by uneven materials, installation deviation, local dust accumulation, etc. It does not reveal the problems caused by the fan impeller structure and cannot well evaluate the dynamic balance state of the impeller during operation.

[0029] Preferably, in one embodiment of the present invention, the dynamic instability index of the analysis period is obtained by combining the change of the area difference of different blades in the impeller edge image in the impeller edge image of consecutive frames, and the specific method includes: For any frame of impeller edge image in the analysis period, several blade areas in the frame of impeller edge image are obtained (obtained directly through edge detection and contour extraction), and the area of ​​each blade area is obtained. The absolute value of the difference between the areas of any two blade areas is obtained, and the average of the absolute values ​​of the difference between the areas of all two blade areas in the frame of impeller edge image is used as the blade area difference factor of the frame of impeller edge image; the absolute value of the difference between the blade area difference factors of any adjacent frame of impeller edge image in the analysis period is obtained, and the product of the average of the absolute values ​​of the difference between the blade area difference factors of all adjacent frame of impeller edge image in the analysis period and the impeller load unevenness in the analysis period is used as the dynamic instability index of the analysis period.

[0030] It should be noted that the blade area hardly changes under ideal conditions during the rotation process. The greater the change in the blade area difference factor, the more likely it is that there is an offset during the rotation of the fan impeller, resulting in large fluctuations in the blade area. Combined with the determined impeller load unevenness, it comprehensively reflects the dynamic disturbance amplitude caused by the uneven load during the rotation of the axial flow fan impeller. It is an important composite feature for measuring the dynamic balance state of the impeller, that is, the larger the dynamic instability index of the fan impeller during rotation.

[0031] It should be further explained that the dynamic stability index mainly reflects the overall dynamic fluctuation trend of the impeller under the influence of various disturbances during operation, but this macroscopic performance cannot deeply reveal the specific cause of the unstable state; further analysis of the inertia distribution and mass eccentricity during the rotation of the impeller can effectively identify whether there are imbalance problems caused by eccentric installation, unilateral overload, bearing wear, etc., providing high-value diagnostic basis for subsequent strategies.

[0032] Preferably, in one embodiment of the present invention, based on the changes in the dynamic instability index in adjacent time periods and the differences between the temperature difference change trends at different positions of the impeller, combined with the changes in the parameter data fluctuations of each key working condition, the impeller dynamic balance deviation in the analysis period is obtained, including the specific method of: For the temperatures of several positions in the impeller at any moment in the analysis period, the absolute value of the temperature difference between any two positions is obtained, and the average of the absolute values ​​of the temperature difference between all two positions in the impeller at that moment is used as the average temperature difference at that moment; a coordinate system is constructed with time as the horizontal axis and temperature difference as the vertical axis, and the average temperature difference at each moment in the analysis period is mapped to the coordinate system to obtain several data points, and the data points are fitted by the least squares method to obtain a fitting straight line and its slope, and the slope is used as the temperature difference change factor of the analysis period; the ratio of the temperature difference change factor of the analysis period to the temperature difference change factor of the adjacent previous period is obtained, and the ratio of the dynamic instability index of the analysis period to the dynamic instability index of the adjacent previous period is obtained, and the product of the two ratios is used as the impeller load trend index of the analysis period.

[0033] It should be noted that the larger the ratio of the dynamic instability index, the greater the change in the dynamic instability index during the analysis period. At the same time, the larger the ratio of the temperature difference change factor, the greater the temperature change, which may cause changes in the physical properties of the material, such as elastic modulus, strength and fatigue life. When the temperature rises, some materials may show softening, resulting in a decrease in dynamic stability.

[0034] It should be further explained that poor dynamic balance is usually accompanied by uneven distribution of loads on each blade, causing some blades to bear excessive force during operation; if the actual working conditions change significantly, then it is possible to have a certain impact on the originally stable impeller, thereby affecting the dynamic balance of the impeller; if the working conditions do not change significantly, it means that the reason for the poor dynamic balance of the fan impeller may be due to partial faults, and timely adjustments are required.

[0035] Furthermore, the standard deviation of all parameter data of any key working condition in the analysis period is obtained, and the standard deviation of all parameter data of the key working condition in the adjacent previous period of the analysis period is obtained. The ratio of the standard deviation corresponding to the key working condition in the analysis period to the standard deviation corresponding to the key working condition in the adjacent previous period is used as the parameter fluctuation change factor of the key working condition in the analysis period.

[0036] Furthermore, based on the impeller load trend index of the analysis period and the mean of the parameter fluctuation change factors of each key working condition in the analysis period, the impeller dynamic balance deviation of the analysis period is obtained. The impeller dynamic balance deviation is positively correlated with the impeller load trend index, and negatively correlated with the mean of the parameter fluctuation change factors of each key working condition.

[0037] As an example, the ratio of the impeller load trend index during the analysis period to the mean value of the parameter fluctuation change factor of each key working condition during the analysis period is used as the impeller dynamic balance deviation during the analysis period.

[0038] It should be noted that the weight is constructed based on the mean of the parameter fluctuation change factors of the key working conditions. The smaller the parameter fluctuation, the less obvious the change in the parameter data of the working condition. The higher the impeller load trend index is caused by the fluctuation of the dynamic balance state, that is, the dynamic balance state suddenly deteriorates, indicating that there may be problems with the dynamic balance state of the equipment, and this situation may be caused by a fault. If certain parts of the impeller are worn or damaged, it may cause uneven distribution of the load, thereby affecting the dynamic balance, and the greater the impeller dynamic balance deviation.

[0039] It should be further explained that after evaluating the dynamic balance deviation of the impeller during the operation of the fan in the analysis period, in the actual operating environment, this dynamic imbalance often not only causes radial vibration, but also further leads to micro-tilt of the rotating axis or axial drift in the main axis direction. The tilt or eccentric state will cause irregular offset of the image observation point, resulting in the break and drift of the feature trajectory in the vertical / depth direction between image frames, further aggravating the difficulty of extracting key feature points.

[0040] Step S003: Obtain the impeller axial deflection index of the analysis period based on the position change of the center of mass and the diameter change of the trajectory area formed by the trajectory of the key points in the impeller edge images of the continuous frames in the analysis period; obtain the impeller structure anomaly index of the analysis period in combination with the grayscale expression change of each blade area in the impeller images of adjacent frames; obtain the visual fusion dynamic balance index of the impeller in the analysis period based on the impeller dynamic balance deviation and the impeller structure anomaly index of the analysis period.

[0041] It should be noted that when analyzing the fan's impeller's tilt and axial offset during rotation, the dynamic balance deviation is mainly manifested as the asymmetry of the rotating mass distribution, and one of the direct spatial manifestations of this asymmetry is axial tilt or center axis offset. Existing industrial cameras cannot accurately obtain visual three-dimensional data information, but can infer the impeller's dynamic balance state in three-dimensional space through the two-dimensional data change characteristics.

[0042] Preferably, in one embodiment of the present invention, the impeller axial deflection index during the analysis period is obtained based on the position change of the center of mass in the trajectory area formed by the trajectory of key points in the impeller edge images of consecutive frames during the analysis period and the diameter change of the trajectory area, including the specific method of: For the position of any key point in each frame of the impeller edge image during the analysis period, the positions in the adjacent frames of the impeller edge image are connected to obtain the movement trajectory of the key point during the analysis period. The movement trajectory forms several closed areas, which are recorded as several trajectory areas. That is, due to the axial deflection of the key point during the rotation process, multiple closed areas are formed as several trajectory areas; the center of mass of each trajectory area and the length of the horizontal straight line passing through the center of mass in the trajectory area are obtained as the horizontal diameter of each trajectory area.

[0043] Furthermore, for several trajectory areas of any key point in the analysis period, the distance between the centroids of any two trajectory areas is obtained, and the horizontal diameters of all trajectory areas of the key point are arranged in ascending order to obtain a horizontal diameter sequence of the key point; the ratio of the latter horizontal diameter to the former horizontal diameter of two adjacent horizontal diameters in the horizontal diameter sequence is obtained, and the mean of the ratios corresponding to all adjacent horizontal diameters in the horizontal diameter sequence is multiplied by the standard deviation of the distances between the centroids of all pairwise trajectory areas of the key point as the axial deflection coefficient of the key point in the analysis period; the mean of the axial deflection coefficients of all key points in the analysis period is taken as the impeller axial deflection index of the analysis period.

[0044] It should be noted that the larger the standard deviation of the distance between the centers of mass, the more likely it is that the impeller is not centered during assembly, or there is an installation error between the shaft and the impeller, which will cause the axial "movement" back and forth during rotation. Large bearing clearance or looseness during operation will cause the impeller to produce irregular axial movement during rotation, resulting in an abnormal increase in drift. The larger the mean of the ratio of adjacent horizontal diameters, the more likely it is that the lateral diameter of the moving trajectory is continuing to increase, indicating that the radial instability during the impeller rotation is increasing, which is a typical manifestation of dynamic balance abnormality. The larger the impeller axial deflection index.

[0045] It should be further explained that if it is caused by the sampling error of the machine vision system, such as lens shake, image blur, etc., it may also be mistakenly judged that the lateral diameter of the impeller edge in the image is too large, that is, the influence of the machine vision sampling error needs to be eliminated.

[0046] Preferably, in one embodiment of the present invention, the impeller structure abnormality index of the analysis period is obtained by combining the grayscale expression changes of each blade area in the impeller images of adjacent frames, and the specific method includes: For any frame impeller image in the analysis period, the number of blade areas in the frame impeller image and the average of the grayscale value means of the pixels in each blade area are obtained, and the product of the number of blade areas and the average of the grayscale value means is used as the grayscale visual representation value of the frame impeller image; the absolute value of the difference between the grayscale visual representation values ​​of any adjacent frame impeller images in the analysis period is obtained.

[0047] Furthermore, based on the impeller axial deflection index of the analysis period and the average of the absolute values ​​of the difference in grayscale visual appearance values ​​of all adjacent frame impeller images in the analysis period, the impeller structure anomaly index of the analysis period is obtained. The impeller structure anomaly index is positively correlated with the impeller axial deflection index, and negatively correlated with the average of the absolute values ​​of the difference in grayscale visual appearance values.

[0048] As an example, the ratio of the impeller axial deflection index in the analysis period to the average of the absolute values ​​of the differences in the grayscale visual representation values ​​of all adjacent frame impeller images in the analysis period is used as the impeller structure abnormality index in the analysis period.

[0049] It should be noted that the smaller the difference in grayscale visual performance values, the smaller the impact of machine vision error on the impeller axial deflection performance. The larger the corresponding impeller axial deflection index, the larger its structural abnormality index. By analyzing the operation process of the impeller in the spatial state, the impeller structural abnormality index in the rotating state is obtained, which can more completely evaluate the dynamic balance state of the fan impeller.

[0050] It should be further explained that based on the obtained impeller structural anomaly index, the non-ideal posture deviation trend in the axial direction is identified, and combined with the impeller dynamic balance deviation characteristics, a multi-dimensional dynamic evaluation model is further established. It not only takes into account the physical characteristic disturbance of the impeller mass distribution, but also integrates the visual change characteristics of the structural response under high-speed rotation, so as to make a more accurate and comprehensive judgment on the dynamic balance state, thereby improving the credibility and operability of the evaluation results.

[0051] Preferably, in one embodiment of the present invention, based on the impeller dynamic balance deviation and the impeller structural abnormality index during the analysis period, the visual fusion dynamic balance index of the impeller during the analysis period is obtained, including the specific method of: The sum of the inverse proportional normalized result of the impeller dynamic balance deviation during the analysis period and the inverse proportional normalized result of the impeller structural abnormality index during the analysis period is used as the visual fusion dynamic balance index of the impeller during the analysis period.

[0052] It should be noted that this embodiment adopts Model to present inverse proportional relationship and normalization processing, is the input of the model, It represents an exponential function with a natural constant as the base. The implementer can set the inverse proportional function and normalization function according to the actual situation.

[0053] It should be noted that the smaller the impeller dynamic balance deviation and the impeller structure abnormality index are, the larger the visual fusion dynamic balance index is under inverse proportion. The comprehensive output between the dynamic balance deviation dimension and the non-ideal posture deviation trend of the impeller in the axial direction can more comprehensively evaluate the dynamic balance state of the fan impeller, indicating that the dynamic balance state of the impeller is better.

[0054] Step S004: adjusting the initial dynamic balance threshold of the impeller based on the visual fusion dynamic balance index, obtaining the adjusted dynamic balance threshold for the analysis period, and performing a dynamic balance assessment of the impeller.

[0055] Based on the design standards of the equipment, the manufacturer's recommended values ​​and the historical operating data, the initial dynamic balance threshold of the impeller is set; the product of the initial dynamic balance threshold of the impeller and the visual fusion dynamic balance index of the impeller during the analysis period is used as the adjusted dynamic balance threshold during the analysis period; and the dynamic balance of the axial flow fan impeller after the analysis period is evaluated based on the adjusted dynamic balance threshold. The specific evaluation process is the existing technology in the field of impeller dynamic balance evaluation and will not be repeated in this embodiment; by dynamically adjusting the dynamic balance threshold, data-driven decision-making is emphasized to ensure that the dynamic balance evaluation mechanism of the equipment can adapt to different operating conditions and improve the reliability and safety of the equipment; at the same time, optimize equipment performance, reduce maintenance costs, and improve overall operational efficiency.

[0056] At this point, this embodiment is completed.

[0057] It should be noted that in the process of calculating the ratio in this embodiment, in order to avoid the denominator being 0 and causing the fraction to be meaningless, a hyperparameter is added to the numerator and denominator for ratio calculation. The hyperparameter in this embodiment is described as 0.1 and will not be repeated in the above ratio calculation process.

[0058] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A machine vision-based axial flow fan impeller dynamic balance assessment method, characterized in that: The method comprises the following steps: The system collects continuous frames of impeller images of a high-speed rotating axial flow fan, obtains impeller edge images of each frame corresponding to the analysis period and several moments therein, extracts several key points from the impeller edge images, and records parameter data of several key operating conditions of the axial flow fan at each moment and the temperature of several locations in the impeller. Based on the smooth performance of the trajectories of key points in the impeller edge images of consecutive frames during the analysis period, and the area distribution of the closed areas formed by the trajectories, the impeller load unevenness during the analysis period is obtained. The dynamic instability index during the analysis period is obtained by combining the changes in the area differences of different blades in the impeller edge images of consecutive frames. Based on the changes in the dynamic instability index of adjacent time periods, the differences in the temperature difference trends at different positions of the impeller, and the changes in the fluctuations of the parameter data of each key working condition, the impeller dynamic balance deviation during the analysis period is obtained. The impeller axial deflection index for the analysis period is obtained based on the position change of the center of mass and the diameter change of the trajectory area formed by the trajectory of key points in the impeller edge images of consecutive frames in the analysis period. The impeller structural anomaly index for the analysis period is obtained by combining the grayscale expression changes of each blade area in the impeller images of adjacent frames. The visual fusion dynamic balance index of the impeller for the analysis period is obtained based on the impeller dynamic balance deviation and the impeller structural anomaly index. The initial dynamic balance threshold of the impeller is adjusted based on the visual fusion dynamic balance index, the adjusted dynamic balance threshold of the analysis period is obtained, and the dynamic balance evaluation of the impeller is performed.

2. The method for evaluating the dynamic balance of an axial flow fan impeller based on machine vision according to claim 1, characterized in that: The method for obtaining the impeller load non-uniformity during the analysis period includes: Fit the position of any key point in the impeller edge image of each frame during the analysis period to obtain the motion trajectory of the key point during the analysis period, and obtain the closed area formed by closing the motion trajectory; divide the closed area into a left area and a right area by a vertical line passing through the center point of the impeller, and obtain the absolute value of the area difference between the left area and the right area as the closed area difference of the key point during the analysis period; Obtain the direction from the previous position of the key point to the next position in any adjacent frame of the impeller edge image during the analysis period as the movement direction of the key point in the previous frame of the adjacent frame during the analysis period; Obtaining the motion direction of the key point in each frame during the analysis period, and multiplying the standard deviation of the angles between the motion directions of the key point in all adjacent frames during the analysis period by the closed area difference as the trajectory nonuniformity of the key point during the analysis period; The mean value of the trajectory unevenness of all key points during the analysis period is taken as the impeller load unevenness during the analysis period.

3. The method for evaluating the dynamic balance of an axial flow fan impeller based on machine vision according to claim 1, characterized in that: The specific method of obtaining the dynamic instability index of the analysis period includes: For any impeller edge image frame in the analysis period, obtain several blade regions in the impeller edge image frame, and obtain the area of ​​each blade region, obtain the absolute value of the difference between the areas of any two blade regions, and take the average of the absolute values ​​of the difference between the areas of all two blade regions in the impeller edge image frame as the blade area difference factor of the impeller edge image frame; The absolute value of the difference between the blade area difference factors of any adjacent frame impeller edge images in the analysis period is obtained, and the average of the absolute values ​​of the difference between the blade area difference factors of all adjacent frame impeller edge images in the analysis period is multiplied by the impeller load non-uniformity in the analysis period as the dynamic instability index of the analysis period.

4. The method for evaluating the dynamic balance of an axial flow fan impeller based on machine vision according to claim 1, characterized in that: The specific method of obtaining the impeller dynamic balance deviation during the analysis period includes: Based on the changes in the dynamic instability index in adjacent periods and the differences in the temperature difference change trends at different impeller positions, the impeller load trend index of the analysis period is obtained; Obtain the standard deviation of all parameter data of any key operating condition in the analysis period, obtain the standard deviation of all parameter data of the key operating condition in the immediately preceding period of the analysis period, and use the ratio of the standard deviation corresponding to the key operating condition in the analysis period to the standard deviation corresponding to the key operating condition in the immediately preceding period as the parameter fluctuation change factor for the key operating condition in the analysis period; Based on the impeller load trend index of the analysis period and the mean value of the parameter fluctuation change factors of each key working condition during the analysis period, the impeller dynamic balance deviation of the analysis period is obtained. The impeller dynamic balance deviation is positively correlated with the impeller load trend index, and negatively correlated with the mean value of the parameter fluctuation change factors of each key working condition.

5. The method for evaluating the dynamic balance of an axial flow fan impeller based on machine vision according to claim 4, characterized in that: The specific method of obtaining the impeller load trend index during the analysis period includes: For the temperatures of several positions in the impeller at any moment in the analysis period, obtain the absolute value of the temperature difference between any two positions, and take the average of the absolute values ​​of the temperature differences between all two positions in the impeller at that moment as the average temperature difference at that moment; A coordinate system is constructed with time as the horizontal axis and temperature difference as the vertical axis. The mean temperature difference at each moment in the analysis period is mapped to the coordinate system to obtain a number of data points. The data points are fitted using the least squares method to obtain a fitting line and its slope, and the slope is used as the temperature difference change factor during the analysis period. The ratio of the temperature difference change factor of the analysis period to the temperature difference change factor of the adjacent previous period is obtained, the ratio of the dynamic instability index of the analysis period to the dynamic instability index of the adjacent previous period is obtained, and the product of the two ratios is used as the impeller load trend index of the analysis period.

6. The method for evaluating the dynamic balance of an axial flow fan impeller based on machine vision according to claim 2, characterized in that: The impeller axial deflection index during the analysis period is specifically obtained as follows: For the position of any key point in each impeller edge image frame during the analysis period, the positions of the key point in the impeller edge images of adjacent frames are connected to obtain the movement trajectory of the key point during the analysis period. The movement trajectory forms several closed areas, which are recorded as several trajectory areas. The center of mass of each trajectory area and the length of the horizontal straight line passing through the center of mass in the trajectory area are obtained as the horizontal diameter of each trajectory area; Based on the distribution of centroids and changes in horizontal diameters in the trajectory area of ​​key points, the axial deflection coefficients of each key point during the analysis period are obtained; The average value of the axial deflection coefficients of all key points during the analysis period is taken as the impeller axial deflection index during the analysis period.

7. The method for evaluating the dynamic balance of an axial flow fan impeller based on machine vision according to claim 6, characterized in that: The axial deflection coefficient of each key point during the analysis period is obtained by: For several trajectory areas of any key point in the analysis period, the distance between the centroids of any two trajectory areas is obtained, and the horizontal diameters of all trajectory areas of the key point are arranged in ascending order to obtain the horizontal diameter sequence of the key point. The ratio of the latter horizontal diameter to the previous horizontal diameter of two adjacent horizontal diameters in the horizontal diameter sequence is obtained, and the mean of the ratios corresponding to all adjacent horizontal diameters in the horizontal diameter sequence is multiplied by the standard deviation of the distances between the centroids of all pairwise trajectory areas of the key point as the axial deflection coefficient of the key point in the analysis period.

8. The method for evaluating the dynamic balance of an axial flow fan impeller based on machine vision according to claim 3, characterized in that: The specific method of obtaining the impeller structure abnormality index during the analysis period includes: For any impeller image frame in the analysis period, the number of blade areas in the impeller image frame and the average of the grayscale values ​​of the pixels in each blade area are obtained, and the product of the number of blade areas and the average of the grayscale values ​​is used as the grayscale visual representation value of the impeller image frame; the absolute value of the difference between the grayscale visual representation values ​​of any adjacent impeller image frames in the analysis period is obtained; Based on the impeller axial deflection index of the analysis period and the average of the absolute values ​​of the difference in grayscale visual appearance values ​​of all adjacent frame impeller images in the analysis period, the impeller structure anomaly index of the analysis period is obtained. The impeller structure anomaly index is positively correlated with the impeller axial deflection index, and negatively correlated with the average of the absolute values ​​of the difference in grayscale visual appearance values.

9. The method for evaluating the dynamic balance of an axial flow fan impeller based on machine vision according to claim 1, characterized in that: The specific method of obtaining the visual fusion dynamic balance index of the impeller during the analysis period includes: The sum of the inverse proportional normalized result of the impeller dynamic balance deviation during the analysis period and the inverse proportional normalized result of the impeller structural abnormality index during the analysis period is used as the visual fusion dynamic balance index of the impeller during the analysis period.

10. The method for evaluating the dynamic balance of an axial flow fan impeller based on machine vision according to claim 1, characterized in that: The specific method of obtaining the adjustment dynamic balance threshold value during the analysis period includes: The product of the initial dynamic balance threshold of the impeller and the visual fusion dynamic balance index of the impeller during the analysis period is used as the adjusted dynamic balance threshold during the analysis period.

Images