Method and device for monitoring the operation of bearing retainers for wind power generation

Abstract

The present invention belongs to the technical field of data monitoring and prediction. Regarding the operating status of conventional wind power units, it is difficult to perform real-time online monitoring and prediction, and there is also a certain delay in the fault reports of wind power units. Therefore, in order to solve the technical problem that it is disadvantageous for quickly maintaining abnormal wind power units, a method and device for monitoring the operation of a bearing retainer for wind power generation are disclosed. The method includes performing multi-point multi-cluster head-assisted tracking on the operating state of a bearing retainer for wind power generation by a plurality of sensor chips pre-provided in the bearing retainer for wind power generation to obtain point tracking information; performing movement vector correction and prediction of related points on the point tracking information after orthogonal coverage to obtain the circular motion trajectory of the points; performing filter processing on the irregular trajectories for the target circular motion trajectory to obtain an ideal circular motion trajectory; and performing probabilistic centroid positioning and comparison on the ideal circular space region and the predicted circular space region to obtain the operation monitoring information of the wind power bearing.

Description

[Technical Field]

[0001] The present application relates to the field of data monitoring and forecasting, and in particular to a method and apparatus for monitoring the performance of a bearing cage for wind power generation. [Background technology]

[0002] Wind power, as a type of green energy, has been developing at an unimaginable speed since the 1980s, and as related technologies have become increasingly mature, it has become a widely used new energy power generation method. Because wind power generation units operate for long periods under complex alternating loads, the requirements for wind power generation transmission systems are becoming increasingly strict, and bearings, as an important component of wind power generation units, play a vital role in ensuring the reliability of the entire unit.

[0003] Currently, the gearboxes, motors, etc. in wind power generation units have a high failure rate, and most of these failures are caused by failure of the wind power generation bearings. Conventionally, a vibration sensor is generally installed inside the wind power generation unit to monitor the operating status of the wind power generation main shaft, thereby monitoring abnormalities in signals such as voltage, current, and power in the wind power generation unit, and indirectly monitoring the operation of the wind power generation bearings or wind power generation bearing cages.

[0004] However, the above-mentioned vibration sensor monitoring method has difficulty in monitoring the operation characteristics of specific operating conditions of wind power bearings or wind power bearing cages, and there is a certain delay, and monitoring is generally only started after a malfunction occurs and severe vibration occurs. Moreover, wind power generation equipment is generally located far away, and the maintenance intervals are very long, which is likely to cause irreparable damage to wind power generation units, blades, hubs, etc., and result in a waste of resources. In addition, it is difficult to monitor and predict the operating conditions of wind power generation main shafts in real time, and it is not possible to provide timely and advance feedback to maintenance staff, which increases the operation and maintenance costs of wind power generation units. Summary of the Invention [Problem to be solved by the invention]

[0005] The embodiments of the present application provide a method and device for monitoring the operation of a bearing cage for wind power generation in order to solve the technical problems that have been encountered in the past: it is difficult to monitor and predict the operation status of a wind power generation unit in real time online, and there is a certain delay in reporting a fault in the wind power generation unit, making it difficult to perform prompt maintenance on a wind power generation unit with an abnormality and significantly increasing maintenance costs. [Means for solving the problem]

[0006] The embodiments of the present application use the following technical means. In one aspect of the present application, an embodiment of the present application provides: a method for obtaining point tracking information by using a plurality of sensor chips pre-installed in a bearing cage for wind power generation to perform multi-point multi-cluster head-assisted tracking of the operating state of the bearing cage for wind power generation, the point tracking information including target coordinate data and corresponding acceleration data of all sensor chips in any period; performing orthogonal coverage of points on the point tracking information, and correcting and predicting motion vectors of related points on the point tracking information after orthogonal coverage to obtain circular motion trajectories of the points, the circular motion trajectories including a target circular motion trajectory and a predicted circular motion trajectory; and determining instantaneous vibration acceleration of the bearing cage for wind power generation based on the vibration acceleration of the bearing cage for wind power generation. The present invention provides an operation monitoring method for a bearing cage for wind power generation, the method comprising: acquiring a vibration circumferential trajectory; performing irregular trajectory filtering on a target circular motion trajectory in the circular motion trajectory using the instantaneous vibration circumferential trajectory to obtain an ideal circular motion trajectory of the bearing cage for wind power generation; generating ideal circumferential spatial domains and corresponding predicted circumferential spatial domains corresponding to the ideal circular motion trajectory and the predicted circular motion trajectory, respectively; performing positioning and matching of probability centers of gravity of the spatial domains for the ideal circumferential spatial domain and the predicted circumferential spatial domain to obtain a predicted overlap spatial domain; determining whether there is an abnormality in the operating status of the bearing cage for wind power generation based on the predicted overlap spatial domain; obtaining operation monitoring information for the wind power bearing; and completing operation monitoring of the wind power generation unit.

[0007] The beneficial effects of the present invention are as follows: By monitoring the operating trajectory of the wind power generation bearing cage in the wind power generation main bearing, it is possible to monitor in real time whether the wind power generation bearing cage actually has an abnormal operating condition based on an error comparison between the predicted overlap space area and the actual overlap space area, and further to predict whether there is an abnormal condition in the wind power generation main shaft and the wind power generation unit, which is useful for providing timely feedback to maintenance staff on possible fault problems and having them arrive at the site immediately, thereby preventing potential faults from progressing; It is useful for real-time online monitoring and prediction of the operating condition of the wind power generation unit, which shortens the delay time in reporting potential faults in the wind power generation unit, which helps to promptly perform maintenance on abnormal wind power generation units, which reduces maintenance costs, and ensures the normal power generation efficiency of the wind power generation unit.

[0008] In one possible embodiment, the multiple sensor chips pre-installed in the wind power bearing cage perform multi-point, multi-cluster head-assisted tracking of the operating status of the wind power bearing cage to obtain point tracking information, specifically, the signal collecting device in the wind power unit collects signals from the multiple sensor chips in the wind power bearing cage to determine whether the wind power bearing cage is operating, and the multiple sensor chips are embedded and evenly distributed in the wind power bearing cage to make the wind power bearing cage rotate balanced; when the wind power bearing cage is operating, the signal sending node of the first sensor chip in operation is determined as the main cluster head node, and the signal sending nodes of the second sensor chip and the third sensor chip are determined as adjacent cluster head nodes; the second sensor chip and the third sensor chip are respectively located adjacent to the first sensor chip on the left and right; calculating the three-dimensional spatial distance of the received signal carrier power associated with the main cluster head node and the adjacent cluster head node according to a predetermined period based on a predetermined RSSI algorithm, respectively, to obtain the main coordinate data and the adjacent coordinate data within the target period, where the main coordinate data and the adjacent coordinate data are both three-dimensional coordinate data; performing a minimum value process of the average spatial distance for the adjacent coordinate data within the target period based on a least squares algorithm, and calculating a median value associated with the spatial distance after the minimum value process to obtain the secondary coordinate data; and determining the point tracking information of all sensor chips from the secondary coordinate data and the target coordinate data of the first sensor chip.

[0009] The beneficial effects of the present application are as follows: A plurality of sensor chips installed in the wind power bearing cage can monitor the operating status of the double-row self-aligning roller bearing in real time, that is, the operating posture and operating trajectory of the wind power bearing cage in three-dimensional space can be tracked in real time by points, and based on the collaborative fusion of multi-cluster heads, each sensor chip can be tracked in real time by its neighboring chips, and main coordinate data and adjacent coordinate data within the target period can be obtained.

[0010] In one possible embodiment, determining point tracking information of all sensor chips from the secondary coordinate data and the target coordinate data of the first sensor chip specifically includes: performing weighted fusion of related coordinate data for the secondary coordinate data in the adjacent cluster head node and the main coordinate data in the main cluster head node according to a target period to obtain the target coordinate data of the first sensor chip; determining the signal transmitting node of the first sensor chip as an adjacent cluster head node according to a preset grid structure of the WSN, and determining the target coordinate data as adjacent coordinate data; and determining the coordinate data of the fourth sensor chip and the target coordinate data of the first sensor chip. After performing a minimum value process of the average spatial distance on the data, the target coordinate data of the second sensor chip is obtained by weighted fusion of the coordinate data, wherein the fourth sensor chip and the first sensor chip are both placed in adjacent positions on the left and right of the second sensor chip; thus, the weighted fusion of the related coordinate data for all sensor chips is performed to determine the target coordinate data of all sensor chips, respectively, and obtain the corresponding acceleration data of the multiple sensor chips during the target period; and determine the point tracking information of all sensor chips from the target coordinate data and corresponding acceleration data of all sensor chips.

[0011] The beneficial effects of the present application are as follows: adjacent cluster head nodes are fused with the main cluster head node to realize weighted fusion of secondary coordinates and main coordinates, which helps to realize target tracking for the main cluster head node based on the adjacent secondary cluster head nodes, that is, to realize tracking for the first sensor chip, and finally obtain the coordinate data and corresponding acceleration data of the related first sensor chip, thus respectively obtaining the point tracking information of the second, third, fourth, etc. sensor chips, and realizing point tracking of all sensor chips in the wind power bearing cage.

[0012] In one possible embodiment, performing orthogonal point coverage on the point tracking information specifically includes: using an orthogonal coverage mechanism to perform point sampling within a target period for target coordinate data corresponding to each sensor chip in the point tracking information, to obtain multi-point position data of associated target coordinate data; dividing a sampling space region corresponding to the point sampling based on the multi-point position data; determining signal strengths associated with the multi-point position data using the sampling space region to obtain signal strength numbers of the associated multi-points; determining a movement trend for the multi-point position data based on the signal strength numbers and the point density in the sampling space region, and using the point with the greatest signal strength in the signal strength numbers as a reference point to determine the movement trend data of the point within the target period; obtaining acceleration data corresponding to each sensor chip in the point tracking signal; and matching the acceleration data with the multi-point position data in the sampling space region in a one-to-one relationship based on the movement trend data of the point, to generate the object circular movement trajectory from the point tracking information.

[0013] The beneficial effects of the present invention are as follows: a sampling space region in a target period is determined according to the point tracking information of each sensor chip, and different signal strength numbers are formed according to the different distances of each sensor chip distance signal collecting device in the sampling space region, which helps to better determine the movement trends of multiple points in the target sampling space region according to the signal strength numbers and the point density and point positions in the sampling space, and then combined with the acceleration of each point, finally form a target circular movement trajectory.

[0014] In one possible embodiment, performing motion vector correction and prediction of related points on point tracking information after orthogonal coverage to obtain a circular motion trajectory of the point specifically includes: obtaining point tracking information after orthogonal coverage in a target period; performing vector prediction of coordinate positions of target coordinate data in the target circular motion trajectory in the next period from acceleration data in the target circular motion trajectory based on a Lagrange interpolation function to obtain predicted target coordinate data; and performing acceleration vector prediction of the next period on acceleration data in the target circular motion trajectory based on positioning distances between points in the target circular motion trajectory. obtaining predicted acceleration data; sampling prediction points with respect to the predicted target coordinate data and dividing them into prediction sampling space regions corresponding to the predicted target coordinate data; determining a predicted motion trend for multiple points in the prediction sampling space region based on the signal strength numbers of the prediction points in the prediction sampling space region and the corresponding prediction point densities; generating a predicted circular motion trajectory for a next period based on the prediction points in the prediction sampling space region and the corresponding predicted acceleration data; and obtaining the circular motion trajectory of the point from the predicted circular motion trajectory and the target circular motion trajectory.

[0015] The beneficial effects of the present application are as follows: the coordinate data and acceleration data of all points in the next period can be further predicted by the Lagrangian difference function, and then a predicted circular motion trajectory corresponding to the target circular motion trajectory can be generated, which is helpful for later comparative prediction of the motion trajectory of the bearing cage for wind power generation.

[0016] In one possible embodiment, obtaining an instantaneous vibration circumferential trajectory of the bearing cage for wind power generation based on the vibration acceleration of the bearing cage for wind power generation specifically includes: obtaining vibration acceleration during a target period with a vibration sensor in a wind power generation unit; performing quaternion differential division on motion trend data during the target circular motion trajectory using a quaternion parameter algorithm to obtain a motion posture matrix of related quaternion differentials; dividing the vibration acceleration during the target period into components in each axial direction in a three-dimensional space based on the motion posture matrix to obtain coordinate data of a vibration vector; performing transient fitting of a circumferential curve to the vibration acceleration and the coordinate data of the vibration vector to obtain a transient fitting curve; and matching a corresponding position to the transient fitting curve according to the three-dimensional space in which the bearing cage for wind power generation is located, thereby determining an instantaneous vibration circumferential trajectory during the target period.

[0017] The beneficial effects of the present invention are as follows: the vibration acceleration acquired by the vibration sensor pre-installed in the wind power generation unit is divided into each axial direction, and then transient curve fitting is performed on the vibration vector data to obtain the instantaneous vibration circumferential locus of the related vibration acceleration, thereby accurately recognizing the offset amount caused by the vibration of the impeller load, and obtaining the instantaneous vibration circumferential locus of the wind power generation bearing cage in the offset amount state.

[0018] In one possible embodiment, obtaining an ideal circular motion locus of the bearing cage for wind power generation by filtering an irregular locus of a target circular motion locus in the circular motion locus using the instantaneous vibration circular locus specifically involves performing linear normalization processing on the instantaneous vibration circular locus and the target circular motion locus to obtain an instantaneous vibration circumferential curve and a target circular curve, respectively, where the instantaneous vibration circumferential curve and the target circular curve are both spiral circumferential curves, and performing differential processing of corresponding coordinate points on the instantaneous vibration circumferential curve and the target circular curve to obtain a plurality of coordinate points. obtaining a distance, performing a median process on the distances of the plurality of coordinate points, to obtain a vibration difference distance; performing curve correction on the target circumferential curve based on the vibration difference distance, to obtain a corrected circumferential curve; performing vector processing on the corrected circumferential curve based on acceleration data in the target circular motion trajectory, to determine a corrected circular motion trajectory; and performing filter screening of an irregular trajectory within a preset error range for the target circular motion trajectory using the corrected circular motion trajectory, to obtain an ideal circular motion trajectory of the bearing cage for wind power generation.

[0019] The beneficial effects of the present invention are as follows: the error of the target circular motion trajectory is corrected by the recognized instantaneous vibration circular trajectory, and the corresponding correction is made to the target circular curve in a timely manner based on the vibration difference distance, so that the true internal operating condition of the wind power generation unit, i.e., the true circular motion trajectory of the wind power generation bearing cage, can be accurately obtained.

[0020] In one possible embodiment, generating an ideal circumferential spatial region corresponding to the ideal circular motion trajectory and the predicted circular motion trajectory and corresponding predicted circumferential spatial region, respectively, and performing positioning and matching of the probability center of gravity of spatial regions for the ideal circumferential spatial region and the predicted circumferential spatial region to obtain a predicted overlap spatial region specifically includes generating a first spiral cylinder corresponding to the ideal circumferential spatial region and a second spiral cylinder corresponding to the predicted circumferential spatial region based on the ideal circular motion trajectory and the predicted circular motion trajectory, respectively, wherein the first spiral cylinder and the second spiral cylinder each include multiple point position information, and obtaining first point position information in the first spiral cylinder. and obtaining a point distribution planar area corresponding to the first point location information based on the significance of a probability distribution function; locating the centroid of a spiral cylinder with respect to the point distribution planar area by a probability density function to obtain first centroid location information of the first spiral cylinder; locating the centroid of the associated point distribution planar area with respect to the second spiral cylinder to obtain second centroid location information of the second spiral cylinder; and performing three-dimensional space overlap matching of the first spiral cylinder and the second spiral cylinder in the same time domain and the same space domain based on the first centroid location information and the second centroid location information to determine a predicted overlap space area where the first spiral cylinder and the second spiral cylinder overlap each other.

[0021] The beneficial effects of the present invention are as follows: based on the circular motion trajectory in three-dimensional space in each period, a motion trajectory quantity with a time component, i.e., a spiral cylinder, is constructed, and then based on the center of gravity position, overlap matching is performed on the space regions where the spiral cylinders in different periods are located to obtain predicted overlap regions, which is useful for monitoring the operation of a bearing cage for wind power generation and predicting the overlapping situations of space regions in different periods under normal conditions.

[0022] In one possible embodiment, determining whether there is an abnormality in the operating status of the wind power generation bearing cage based on the predicted overlap spatial area, and obtaining operation monitoring information for the wind power bearing, specifically includes: determining a third spiral cylinder of a related actual circumferential spatial area based on an actual circular motion trajectory corresponding to a next period, where the actual circular motion trajectory is a point circular motion trajectory for a next period from the ideal circular motion trajectory; locating the center of gravity of the related point distribution plane area with respect to the third spiral cylinder to obtain third center of gravity position information of the third spiral cylinder; performing three-dimensional space overlap matching of the first spiral cylinder and the third spiral cylinder in the same time domain and the same space domain based on the third center of gravity position information to obtain a true overlap spatial area; determining whether there is an abnormality in the operating status of the wind power generation bearing cage based on spatial area size determination information of the true overlap spatial area and the predicted overlap spatial area, obtaining operation monitoring information for the wind power bearing, and completing operation monitoring of the wind power generation unit.

[0023] In another aspect, an embodiment of the present application also provides an operation monitoring device for a bearing cage for wind power generation, including at least one processor and a memory communicatively connected to the at least one processor, wherein the memory stores instructions executable by the at least one processor, thereby enabling the at least one processor to execute the operation monitoring method for a bearing cage for wind power generation described in any of the above embodiments.

[0024] The beneficial effects of the present invention are as follows: By monitoring the operating trajectory of the wind power generation bearing cage in the wind power generation main bearing, it is possible to monitor in real time whether the wind power generation bearing cage actually has an abnormal operating condition based on an error comparison between the predicted overlap space area and the actual overlap space area, and further to predict whether there is an abnormal condition in the wind power generation main shaft and the wind power generation unit, which is useful for providing timely feedback to maintenance staff on possible fault problems and having them arrive at the site immediately, thereby preventing potential faults from progressing; It is useful for real-time online monitoring and prediction of the operating condition of the wind power generation unit, which shortens the delay time in reporting potential faults in the wind power generation unit, which helps to promptly perform maintenance on abnormal wind power generation units, which reduces maintenance costs, and ensures the normal power generation efficiency of the wind power generation unit. [Brief explanation of the drawings]

[0025] In order to more clearly describe the technical solutions of the embodiments of the present application or the prior art, the following briefly introduces drawings to be used in the description of the embodiments or the prior art. It goes without saying that the drawings in the following description are only some of the embodiments described in the present application, and those skilled in the art can also obtain other drawings based on these drawings without performing any novel work. In the drawings,

[0026] [Figure 1] FIG. 1 is a flowchart of a method for monitoring the operation of a bearing cage for wind power generation provided by an embodiment of the present application. [Figure 2] FIG. 2 is a structural schematic diagram of a double-row self-aligning roller bearing provided by an embodiment of the present application. [Figure 3] FIG. 3 is a structural schematic diagram of the operational monitoring for the wind power bearing provided by the embodiment of the present application. [Figure 4] FIG. 4 is a schematic diagram of the sensor chip distribution of a bearing cage for wind power generation provided by an embodiment of the present application. [Figure 5]FIG. 5 is a structural schematic diagram of a performance monitoring device for a bearing cage for wind power generation provided by an embodiment of the present application. DETAILED DESCRIPTION OF THE INVENTION

[0027] In order to allow those skilled in the art to better understand the technical solutions of the present application, the technical solutions of the embodiments of the present application will be described below clearly and completely with reference to the drawings of the embodiments of the present application, and it goes without saying that the described embodiments are only a part of the embodiments of the present application, and are not all of the embodiments, and all other embodiments that those skilled in the art can obtain from the embodiments of the present application without any novel work shall fall within the protection scope of the present application.

[0028] An embodiment of the present application provides a method for monitoring the operation of a bearing cage for wind power generation, and as shown in FIG. 1, the method for monitoring the operation of a bearing cage for wind power generation specifically includes steps S101 to S106. The wind power transmission main shaft of the wind power unit in the wind power generation device is equipped with two wind power bearings, and generally uses double-row self-aligning roller bearings. For example, FIG. 2 is a structural schematic diagram of a double-row self-aligning roller bearing provided by an embodiment of the present application. As shown in FIG. 2, the self-aligning roller bearing has two rows of rollers and is fixed and held by a bearing cage. During the operation of the wind power unit, a certain load pressure is applied to the main shaft, causing the center of gravity of the main shaft to be offset. Therefore, due to the characteristics of the self-aligning roller bearing, a certain offset can be realized in the main shaft. The wind power bearing cage will have a certain offset in its movement according to the offset of the main shaft, that is, not only in horizontal rotation but also in all directional angles. Therefore, by monitoring the movement trajectory of the wind power bearing cage, the operation of the wind power bearing can be monitored, which can better reflect the operation status of the wind power main shaft and, therefore, the operation status of the entire wind power unit.

[0029] In step S101, a plurality of sensor chips are pre-installed in the wind power bearing cage to carry out multi-point multi-cluster head-assisted tracking of the operating state of the wind power bearing cage, and obtain point tracking information, which includes the target coordinate data and corresponding acceleration data of all sensor chips in any period.

[0030] Specifically, a signal collecting device in a wind power generation unit collects signals from multiple sensor chips in a wind power generation bearing cage to determine whether the wind power generation bearing cage is operating. The multiple sensor chips are embedded and evenly distributed in the wind power generation bearing cage to adjust the wind power generation bearing cage to rotational balance. When the wind power generation bearing cage is operating, the signal transmitting node of the first sensor chip in operation is determined as the main cluster head node, and the signal transmitting nodes of the second and third sensor chips are determined as adjacent cluster head nodes. The second and third sensor chips are located adjacent to the first sensor chip on the left and right, respectively.

[0031] In one embodiment, Figure 4 is a schematic diagram of the distribution of sensor chips in a wind power bearing cage provided by an embodiment of the present application. As shown in Figure 4, when manufacturing a wind power bearing cage compatible with a double-row self-aligning roller bearing, several sensor chips are inserted into the wind power bearing cage through a pressing process or an integrated manufacturing process, and are evenly distributed inside the cage so that the cage meets the dynamic balance requirements during operation and ensures normal and stable operation of the cage. According to the arrangement method shown in Figure 4, eight sensor chips are arranged one on each side. In addition, the sensor chips have a signal transmission function that transmits real-time coordinate data and acceleration data, and the signal collection device collects the transmitted signals.

[0032] In one embodiment, Figure 3 is a structural schematic diagram of the operational monitoring of wind power bearings provided by an embodiment of the present application, as shown in Figure 3, a signal server connected to a signal collecting device in a wind power unit performs multi-point multi-cluster head assisted tracking for the operating wind power bearing holder, and uses different levels of cluster heads to complete different tasks at different stages, so as to improve the positioning tracking accuracy of the sensor chip and reduce the target loss rate of points, and divide the cluster heads into main cluster head nodes and secondary cluster head nodes.

[0033] Furthermore, according to a preset RSSI (Received Signal Strength Indicator) algorithm, the three-dimensional spatial distance of the received signal carrier power associated with the main cluster head node and the adjacent cluster head node is calculated for a preset period, respectively, to obtain the main coordinate data and the adjacent coordinate data within the target period, respectively. The main coordinate data and the adjacent coordinate data are both three-dimensional coordinate data.

[0034] In one embodiment, in the signal receiving device, based on the RSSI algorithm, the relative distance of the received signal carrier power is calculated for the determined main cluster head node and the neighboring cluster head node, and d y =d0×10((P0-P y ) / α), d x =d0×10((P0-P x ) / β) and d z =d0×10((P0-P z ) / γ), where α, β, and γ are coordinate reference intermediate quantities, P0 is the reference signal carrier power, and P y , P x , P z are the carrier powers in the y, x, and z axis directions, respectively, and d0 is a preset reference signal receiving distance. Next, the main coordinate data and adjacent coordinate data within the target period are respectively determined.

[0035] Furthermore, based on the least squares algorithm, the minimum value of the average spatial distance is processed for the adjacent coordinate data within the target period, and the median value associated with the spatial distance after the minimum value processing is calculated to obtain secondary coordinate data.

[0036] In one embodiment, two adjacent coordinate data within a target period are represented by a matrix using multilateration to obtain a matrix A corresponding to the second sensor chip and a matrix B corresponding to the third sensor chip, respectively. Since there may be a ranging error, a random error vector is added, and combined with a least squares algorithm, a minimum value process is performed on the average spatial distance between matrix A and matrix B. Then, a median differentiation is performed on the average spatial distance after the minimum value process, and finally, secondary coordinate data in which the two adjacent coordinates are mapped to each other is obtained.

[0037] Furthermore, according to the target period, weighted fusion of the associated coordinate data is performed on the secondary coordinate data in the adjacent cluster head node and the main coordinate data in the main cluster head node to obtain the target coordinate data of the first sensor chip.

[0038] In one possible embodiment, the secondary coordinate data in the adjacent cluster head node is sent to the main cluster head node, and then, based on the difference in the weighting ratio of the secondary coordinate data and the main coordinate data, the two are divided without weighting, i.e., the secondary coordinate data is merged with the main coordinate data, thereby reducing the tracking positioning error occurring in the process of positioning the first sensor chip by single tracking and ensuring the accuracy of the positioning tracking of the main coordinate data in the main cluster head node.

[0039] Furthermore, based on the preset grid structure of the WSN (wireless sensor network), the signal transmitting node of the first sensor chip is first determined as the adjacent cluster head node, and the target coordinate data is determined as the adjacent coordinate data. After performing a minimum average spatial distance process on the coordinate data of the fourth sensor chip and the target coordinate data of the first sensor chip, the target coordinate data of the second sensor chip is obtained by weighted fusion of the coordinate data. The fourth sensor chip and the first sensor chip are both positioned adjacent to each other on the left and right of the second sensor chip. In this way, weighted fusion of the associated coordinate data of all sensor chips is performed to determine the target coordinate data of all sensor chips. Corresponding acceleration data during the target period of multiple sensor chips is obtained. Next, point tracking information of all sensor chips is finally determined from the target coordinate data and corresponding acceleration data of all sensor chips.

[0040] In one possible embodiment, as shown in Figure 4, the point tracking of the remaining sensors is performed in sequence according to the point tracking of the first sensor chip, in this way the second sensor chip, the third sensor chip, the fourth sensor chip, etc. are determined in this order as the main cluster head node, and the corresponding adjacent sensor chips are determined in sequence as the adjacent cluster head nodes, finally obtaining the target coordinate data of each sensor chip, and then obtaining the acceleration data of each sensor chip in the corresponding period according to the period in which each sensor chip is located, and finally determining the acceleration data and target coordinate data of each sensor chip as the point tracking information of the point in which the sensor chip is located.

[0041] In step S102, the point tracking information is subjected to orthogonal coverage of the points, and the motion vectors of the related points are corrected and predicted for the point tracking information after the orthogonal coverage to obtain circular motion trajectories of the points, which include a target circular motion trajectory and a predicted circular motion trajectory.

[0042] Specifically, by using an orthogonal coverage mechanism, point sampling is performed in a target period for the target coordinate data corresponding to each sensor chip in the point tracking information to obtain multi-point position data of the associated target coordinate data, and then a sampling space region corresponding to the point sampling is divided according to the multi-point position data.

[0043] In one embodiment, by extracting any two sampling samples in the point tracking information, sampling division is performed on the three-dimensional coordinates corresponding to the two points, and then orthogonal coverage is performed on the above two points, i.e., sample point 1 (X1, Y1, Z1) and sample point 2 (X2, Y2, Z2) based on the orthogonal mechanism, and then X fin = βX1 + αX2, Y fin = βY1 + αY2, Z fin = βZ1 + αZ2, the multi-point position data, that is, the multi-point position coordinates (X fin ,Y fin ,Z fin ) is obtained, and then divided into sampling space regions corresponding to the sampling points based on the position data after sampling, where α and β are orthogonal coverage intermediate quantities.

[0044] Furthermore, the signal strength associated with the location data of the multi-points is determined through the sampling space domain, and the signal strength number of the associated multi-points is obtained. Furthermore, the movement trend is determined for the location data of the multi-points based on the signal strength number and the point density in the sampling space domain, and the point with the maximum signal strength among the signal strength numbers is taken as the reference point to determine the movement trend data of the points in the target period.

[0045] In one embodiment, P(N)=L((ε(d1-d0) 2) / μ), determine the signal strength associated with the position data of the sampling area, and obtain the signal strength number P(N) of each point, where L is the point density, μ is the sampling space area, d1 is the signal receiving distance between the point and the signal collecting device, d0 is the inherent error distance, and ε is the signal frequency parameter. Then, mark each point according to the signal strength number of each point, and then determine the movement trend of the position data of the multi-points according to the mark number. The point with the strongest signal strength is taken as the reference point, and finally determine the movement trend data of the point in the target period.

[0046] In addition, the acceleration data corresponding to each sensor chip in the point tracking signal is first obtained, and the acceleration data is matched one-to-one with the position data of multiple points in the sampling space domain based on the point motion trend data, thereby generating an object circular motion trajectory from the point tracking information.

[0047] Furthermore, point tracking information after orthogonal coverage in the target period is obtained. Based on the Lagrange interpolation function, a vector prediction of the coordinate position of the target coordinate data in the target circular motion trajectory in the next period is performed from the acceleration data in the target circular motion trajectory to obtain predicted target coordinate data.

[0048] In one embodiment, the point coordinates of the WSN (wireless sensor network) in the point tracking information after orthogonal coverage are all one-time coordinates, and the WSN point coordinates in the next period may enter a new coverage area according to their own movement. Since the moving wireless sensor network node is in a low speed state and the coverage radius is generally 10m or more, the point tracking information within a period of 1 second can all be located within the orthogonal coverage area of ​​the sampling space region in that period. Then, the corresponding coordinates in the k period are (X k ,Y k ,Z k) and the value of the corresponding k period is predicted using the Lagrangian interpolation function L(k). That is, Lagrangian prediction is performed by obtaining target coordinate data for the target k period using the Lagrangian interpolation function L(k), and the predicted target coordinate data (X (k+1) ,Y (k+1) ,Z (k+1) ) can be obtained.

[0049] In one possible embodiment, L(i)=Σ i k=0 [L(k-2)-L(k-3)] / Σ i k=0 (t k -t k-1 ) to obtain the Lagrangian interpolation function L(i) for the target k period, where t k is the amount of time in the k period, and t k-1 is the amount of time in the k-1 period, and L is the point density. Next, the x-axis coordinate value for the k period: X k =L(t)=L1X k-1 +L2X k-2 where L(t) is the Lagrange interpolation function for the t time period, and the coordinate value X of the x-axis for the k+1 time period k+1 In this way, the y-axis coordinate and z-axis coordinate for the k+1 period are obtained, and finally the predicted target coordinate data (X k+1 ,Y k+1 ,Z k+1 ) is obtained.

[0050] Furthermore, based on the positioning distances between each point on the target circular motion trajectory, a vector prediction of the acceleration of the next period is performed on the acceleration data on the target circular motion trajectory to obtain predicted acceleration data. Next, predicted points are sampled for the predicted target coordinate data. A predicted sampling space region corresponding to the predicted target coordinate data is divided.

[0051] In one embodiment, the limit value d in each axis direction of the orthogonal coverage of each node in the target circular motion trajectory in the sampling space domain is i Then R i=min(r,d i ) based on the positioning distance R between each point in the target circular motion trajectory. i where r is the reference radial distance of each node. Furthermore, using the Lagrangian interpolation function L(i) for the target k period, the acceleration vector for the k+1 period is predicted for the acceleration data in the target circular motion trajectory to obtain the predicted speed for the k+1 period of the acceleration vector for each axis direction, i.e., the x-axis, y-axis, and z-axis. Next, the speeds in the three axis directions are vector-added to obtain the acceleration data for each point in the k+1 period, where the x-axis and y-axis are coordinate axes on the same plane of the roller, and the z-axis is the direction of the wind power generation main axis.

[0052] Furthermore, a predicted motion trend is determined for multiple points in the predicted sampling space region based on the signal strength number of the predicted points in the predicted sampling space region and the corresponding predicted point density. After matching the predicted acceleration data with the predicted points in the predicted sampling space region, a predicted circular motion trajectory for the next period is generated. The circular motion trajectory of the point is obtained from the predicted circular motion trajectory and the target circular motion trajectory.

[0053] In one possible embodiment, after obtaining predicted target coordinate data and corresponding acceleration data, point sampling is performed for the next period on the predicted target coordinate data corresponding to each sensor chip in the predicted point tracking information to obtain predicted multi-point position data for the associated predicted target coordinate data. Further, a predicted sampling space region corresponding to the point sampling is divided based on the predicted multi-point position data. Using the predicted sampling space region, a signal strength associated with the predicted multi-point position data is determined to obtain a signal strength number for the associated predicted multi-point. Further, a predicted motion trend is determined for the multi-point position data based on the signal strength number and the point density in the predicted sampling space region. The obtained predicted acceleration data is matched with the predicted points in the predicted sampling space region, and a predicted circular motion trajectory for the next period is generated.

[0054] In S103, an instantaneous vibration circumferential locus of the bearing cage for wind power generation is obtained based on the vibration acceleration of the bearing cage for wind power generation.

[0055] Specifically, first, the vibration acceleration during the target period is acquired by a vibration sensor in the wind power generation unit, and then the quaternion parameter algorithm is used to perform quaternion differential division on the motion trend data during the target circular motion trajectory to obtain the motion posture matrix of the relevant quaternion differential.

[0056] Furthermore, based on the motion posture matrix, the vibration acceleration during the target period is divided into components in each axial direction in three-dimensional space to obtain coordinate data of the vibration vector. Next, transient fitting of a circumferential curve is performed on the coordinate data of the vibration acceleration and the vibration vector to obtain a transient fitting curve.

[0057] Furthermore, according to the three-dimensional space where the wind power generation bearing cage is located, the corresponding positions are then matched against the transient fitting curve to determine the instantaneous vibration circumferential locus during the target period.

[0058] In one embodiment, first, the vibration acceleration during the target period is obtained using a vibration sensor inside the wind power generation unit. Then, based on the transformation relationship between absolute coordinates and relative coordinates, a coordinate transformation is performed on the motion trend data in the target circular motion trajectory, i.e., a data transformation between the target coordinate data and acceleration data of each point, using a quaternion to generate a quaternion differential equation. Next, a matrix transformation is performed on the quaternion differential equation to generate a motion posture matrix of the relevant quaternion differential.

[0059] In one embodiment, the quaternion parameters in the motion posture matrix are used to divide the components of the vibration acceleration in the target period along the x-axis, y-axis, and z-axis to generate a vibration acceleration component matrix in each associated axial direction; then, through an integration operation, a relevant circular curve is transiently fitted to the vibration acceleration component matrix to obtain a transient fitting curve; then, by matching each corresponding point in the same period with the transient fitting curve and the three-dimensional space in which the target circular motion trajectory is located, the transient fitting curve and the target circular motion trajectory are located in the same circular space region in time and space; then, from the corresponding vibration acceleration and transient fitting circular motion trajectory, the instantaneous vibration circular trajectory in the target period is determined.

[0060] In S104, an irregular locus is filtered out of the target circular motion locus among the circular motion loci using the instantaneous vibration circular motion locus, thereby obtaining an ideal circular motion locus of the bearing cage for wind power generation.

[0061] Specifically, the instantaneous vibration circular trajectory and the target circular motion trajectory are first subjected to linear normalization to obtain the instantaneous vibration circular curve and the target circular curve, respectively. The instantaneous vibration circular curve and the target circular curve are both spiral circular curves.

[0062] Furthermore, first, a difference process is performed on the corresponding coordinate points of the instantaneous vibration circular curve and the target circular curve to obtain the distances of the multiple coordinate points, and then a median process is performed on the distances of the multiple coordinate points to obtain the vibration difference distance.

[0063] Furthermore, based on the vibration difference distance, a curve correction is then performed on the target circular curve to obtain a corrected circular curve. Based on the acceleration data in the target circular motion trajectory, vector processing is performed on the corrected circular curve to determine a corrected circular motion trajectory. Next, using the corrected circular motion trajectory, irregular trajectories are filtered out within a preset error range for the target circular motion trajectory to obtain an ideal circular motion trajectory for the bearing cage for wind power generation.

[0064] In one embodiment, first, a linear normalization process is performed on the instantaneous vibration circular trajectory and the target circular motion trajectory to obtain an instantaneous vibration circular curve and a target circular curve for comparison calculation. Then, the difference between the corresponding coordinate points of the instantaneous vibration circular curve and the target circular curve is calculated to determine the vibration difference distance of each point, which helps to eliminate vibration from the target circular curve and ensure the uniformity and completeness of the target circular curve. Next, the corrected circular motion trajectory is used to filter out irregular trajectories within a preset error range for the target circular motion trajectory, thereby obtaining an ideal circular motion trajectory for the wind power generation bearing cage.

[0065] In step S105, a corresponding ideal circumferential spatial region and a corresponding predicted circumferential spatial region are generated for the ideal circular motion trajectory and the predicted circular motion trajectory, respectively, and a predicted overlap spatial region is obtained by performing positioning and matching of the probability center of gravity of the spatial region for the ideal circumferential spatial region and the predicted circumferential spatial region.

[0066] Specifically, a first spiral cylinder corresponding to the ideal circular space region and a second spiral cylinder corresponding to the predicted circular space region are generated based on the ideal circular motion trajectory and the predicted circular motion trajectory, respectively, and each of the first spiral cylinder and the second spiral cylinder includes multiple point position information.

[0067] Further, first point position information in the first spiral cylinder is obtained. Then, a point distribution planar region corresponding to the first point position information is obtained based on the significance of the probability distribution function. The centroid of the spiral cylinder is located with respect to the point distribution planar region using the probability density function to obtain first centroid position information of the first spiral cylinder. Then, the centroid of the associated point distribution planar region is located with respect to the second spiral cylinder to obtain second centroid position information of the second spiral cylinder.

[0068] Furthermore, based on the first centroid position information and the second centroid position information, overlap matching is performed in three-dimensional space for the first spiral cylinder and the second spiral cylinder in the same time domain and the same spatial domain, and a predicted overlap spatial domain where the first spiral cylinder and the second spiral cylinder overlap each other is determined.

[0069] In one embodiment, based on the three-dimensional data display of the ideal circular motion trajectory and the predicted circular motion trajectory, a first spiral cylinder corresponding to the ideal circular spatial region and a second spiral cylinder corresponding to the predicted circular spatial region are generated, respectively, where the spatial position and spiral angle of the spiral cylinder vary depending on the period. The significance of the first point position information in the first spiral cylinder is then recognized using the significance of the probability distribution function, and a point distribution planar region corresponding to the first point position information is obtained. The probability density function is then used to locate the centroid of the spiral cylinder relative to the point distribution planar region, and the centroid position data of the first spiral cylinder is recognized to obtain first centroid position information for the first spiral cylinder. In this manner, the centroid of the associated point distribution planar region is then located relative to the second spiral cylinder, and the centroid position data of the second spiral cylinder is recognized to finally obtain second centroid position information for the second spiral cylinder.

[0070] In one possible embodiment, based on the first centroid position information and the second centroid position information, corresponding movement processing of the spiral cylinders is performed for the first spiral cylinder and the second spiral cylinder in three-dimensional space in the same time domain and the same spatial domain; then, based on each corresponding point position, spatial volumes are superimposed for the first spiral cylinder and the second spiral cylinder; then, a predicted overlapping spatial region where the first spiral cylinder and the second spiral cylinder overlap each other is determined, so as to recognize the trajectory parts of the same circular trajectory between the ideal circular motion trajectory and the predicted circular motion trajectory, and remove the trajectory parts of the different circular trajectories.

[0071] In S106, it is determined whether there is an abnormality in the operating status of the wind power generation bearing cage based on the predicted overlap space region, and operation monitoring information of the wind power generation bearing is obtained, thereby completing the operation monitoring of the wind power generation unit.

[0072] Specifically, the third spiral cylinder of the associated actual circular space region is determined based on the actual circular motion trajectory corresponding to the next period, where the actual circular motion trajectory is the point circular motion trajectory of the next period from the ideal circular motion trajectory.

[0073] Furthermore, the centroid of the associated point distribution planar region is located relative to the third spiral cylinder to obtain third centroid position information of the third spiral cylinder.

[0074] Furthermore, based on the third centroid position information, overlap matching of the three-dimensional space of the same time domain and the same space domain is performed for the first spiral cylinder and the third spiral cylinder to obtain a true overlapping space domain.

[0075] Furthermore, based on the spatial area size determination information of the actual overlap spatial area and the predicted overlap spatial area, it is determined whether there is an abnormality in the operating status of the wind power generation bearing cage, and operation monitoring information for the wind power generation bearing is obtained, thereby completing the operation monitoring of the wind power generation unit.

[0076] In one embodiment, first obtain the corresponding actual circular motion trajectory in the next period, and construct a third spiral cylinder of the relevant actual circumferential space region, that is, a spiral cylinder corresponding to the motion trajectory of the wind power bearing cage in the next period; then perform spatial volume matching on the related center of gravity position information between the third spiral cylinder and the first spiral cylinder in the target period to obtain the true overlapping space region between the first spiral cylinder and the third spiral cylinder, that is, the actual point circular motion trajectory of the wind power bearing cage from the target period to the next period; then compare the overlapping degree of the three-dimensional space in the same time and space domain between the true overlapping space region and the predicted overlapping space region; the higher the overlapping degree, the more the operating condition of the wind power bearing cage conforms to the normal operating condition, that is, the more the operating condition of the wind power bearing conforms to the normal operating condition. Conversely, the lower the overlap degree, the more the operating condition of the wind power generation bearing cage deviates from the normal operating condition, the more obvious the abnormal condition of the wind power generation bearing is, and the more likely it is that potential failures will occur.Finally, the operating monitoring information of the wind power generation bearing is sent to the maintenance staff by the server in the wind power generation unit, realizing real-time operating monitoring of the wind power generation unit, which allows the maintenance staff to timely discover potential failures in abnormal operating conditions, and helps the maintenance staff to prepare maintenance plans in advance to prevent the expansion of the wind power generation unit failure and to preempt the risk of potential abnormalities that may cause major failures.

[0077] Furthermore, an embodiment of the present application provides an operation monitoring device for a bearing cage for wind power generation. As shown in FIG. 5, the operation monitoring device 500 for a bearing cage for wind power generation specifically includes: The system includes at least one processor 501 and a memory 502 communicatively connected to the at least one processor. The memory 502 stores instructions executable by the at least one processor 501, thereby causing the at least one processor 501 to: A plurality of sensor chips are pre-installed in the wind power generation bearing cage, and multi-cluster head-assisted multi-point tracking is performed on the operating status of the wind power generation bearing cage to obtain point tracking information, and the point tracking information includes target coordinate data and corresponding acceleration data of all sensor chips in any period; Performing orthogonal coverage of points on the point tracking information, and performing motion vector correction and prediction of related points on the point tracking information after the orthogonal coverage to obtain circular motion trajectories of the points, wherein the circular motion trajectories include a target circular motion trajectory and a predicted circular motion trajectory; acquiring an instantaneous vibration circumferential locus of the bearing cage for wind power generation based on the vibration acceleration of the bearing cage for wind power generation; By using the instantaneous vibration circular locus, irregular locus filtering is performed on the target circular motion locus among the circular motion loci to obtain an ideal circular motion locus of the bearing cage for wind power generation. generating corresponding ideal circumferential spatial regions and corresponding predicted circumferential spatial regions for the ideal circular motion trajectory and the predicted circular motion trajectory, respectively, and performing positioning and matching of the probability centers of gravity of the spatial regions for the ideal circumferential spatial region and the predicted circumferential spatial region to obtain a predicted overlap spatial region; Based on the predicted overlap space area, it is possible to determine whether there is an abnormality in the operating status of the wind power generation bearing retainer, obtain operating monitoring information for the wind power generation bearing, and complete operating monitoring for the wind power generation unit.

[0078] The beneficial effects of the present invention are as follows: By monitoring the operating trajectory of the wind power generation bearing cage in the wind power generation main bearing, it is possible to monitor in real time whether the wind power generation bearing cage actually has an abnormal operating condition based on an error comparison between the predicted overlap space area and the actual overlap space area, and further to predict whether there is an abnormal condition in the wind power generation main shaft and the wind power generation unit, which is useful for providing timely feedback to maintenance staff on possible fault problems and having them arrive at the site immediately, thereby preventing potential faults from progressing; It is useful for real-time online monitoring and prediction of the operating condition of the wind power generation unit, which shortens the delay time in reporting potential faults in the wind power generation unit, which helps to promptly perform maintenance on abnormal wind power generation units, which reduces maintenance costs, and ensures the normal power generation efficiency of the wind power generation unit.

[0079] In this application, each embodiment is described in a chain-like manner, and reference may be made to the same or similar parts between the embodiments, and the description of each embodiment will focus on the differences from other embodiments. In particular, the device and non-volatile computer storage medium embodiments are similar to the method embodiments, so they are briefly described, and reference may be made to the description of the method embodiments for related parts.

[0080] The above describes specific embodiments of the present application. In some cases, the actions or steps described in the specification can be performed in a different order than the examples and still achieve desirable results. Also, the processes depicted in the figures do not necessarily achieve desirable results in the particular order or sequential order shown. In some embodiments, multitasking or parallel processing may be possible or beneficial.

[0081] The above-mentioned are merely examples of the present application and are not intended to limit the present application. Those skilled in the art may have various modifications and variations to the present application. Any amendments, equivalent replacements, improvements, etc. made within the spirit and principle of the present application shall be included in the scope of the specification of the present application.

Claims

1. A method for monitoring the operation of a bearing cage for wind power generation, comprising: A plurality of sensor chips are pre-installed in the wind power generation bearing cage to perform multi-point, multi-cluster head-assisted tracking of the operating status of the wind power generation bearing cage to obtain point tracking information, specifically: A signal collecting device in a wind power generation unit collects signals from a plurality of sensor chips in the wind power generation bearing cage to determine whether the wind power generation bearing cage is operating, and the plurality of sensor chips are embedded and evenly distributed in the wind power generation bearing cage and make the wind power generation bearing cage fit for rotation balance; When the bearing cage for wind power generation is operating, determine the signal transmitting node of the first sensor chip in operation as a main cluster head node, and determine the signal transmitting nodes of the second sensor chip and the third sensor chip as adjacent cluster head nodes, where the second sensor chip and the third sensor chip are respectively located at positions adjacent to the first sensor chip on the left and right; According to a preset RSSI algorithm, calculate three-dimensional spatial distances of received signal carrier powers associated with the main cluster head node and the neighboring cluster head node according to a preset target period, respectively, to obtain main coordinate data and neighboring coordinate data within the target period, respectively, where the main coordinate data and neighboring coordinate data are three-dimensional coordinate data; Based on a least squares algorithm, perform a minimum value process of the average spatial distance for the adjacent coordinate data within the target period, and calculate a median value related to the spatial distance after the minimum value process to obtain secondary coordinate data; determining point tracking information of all sensor chips from the secondary coordinate data and the target coordinate data of the first sensor chip, the point tracking information including target coordinate data and corresponding acceleration data of all sensor chips in any time period; determining point tracking information of all sensor chips from the secondary coordinate data and the target coordinate data of the first sensor chip specifically includes: performing weighted fusion of related coordinate data for the secondary coordinate data in the neighboring cluster head node and the main coordinate data in the main cluster head node according to a target time period to obtain the target coordinate data of the first sensor chip; Performing orthogonal coverage of points on the point tracking information, specifically: By using an orthogonal coverage mechanism, perform point sampling in a target period for the target coordinate data corresponding to each sensor chip in the point tracking information to obtain multi-point position data of the related target coordinate data; Dividing the multi-point position data into sampling space regions corresponding to the point sampling; determining a signal strength associated with the location data of the multi-points according to the sampling space domain, and obtaining a signal strength number of the associated multi-points; According to the signal strength number and the point density in the sampling space region, determining a movement trend for the position data of the multi-points, and determining the movement trend data of the points in the target period by taking the point with the maximum signal strength in the signal strength number as a reference point; Acquiring acceleration data corresponding to each sensor chip in the point tracking information, and according to the motion trend data of the points, matching the acceleration data with the position data of multiple points in the sampling space domain in a one-to-one manner to generate an object circular motion trajectory from the point tracking information; and performing motion vector correction and prediction of related points in the point tracking information after orthogonal coverage to obtain the circular motion trajectory of the points, specifically: Obtaining point tracking information after orthogonal coverage for a target period; performing a vector prediction of a coordinate position for a next period with respect to target coordinate data in the target circular motion trajectory based on the acceleration data in the target circular motion trajectory based on a Lagrange interpolation function, thereby obtaining predicted target coordinate data; performing a vector prediction of acceleration for a next period on the acceleration data in the target circular motion trajectory based on positioning distances between each point in the target circular motion trajectory to obtain predicted acceleration data; sampling predicted points for the predicted target coordinate data and dividing the predicted sampling space into predicted sampling space regions corresponding to the predicted target coordinate data; Determine a predicted motion trend for multiple points in the prediction sampling space region according to the signal intensity numbers of the prediction points in the prediction sampling space region and the corresponding prediction point densities, and generate a predicted circular motion trajectory for a next period according to the prediction points in the prediction sampling space region and the corresponding predicted acceleration data; obtaining a circular motion trajectory of the point from the predicted circular motion trajectory and the target circular motion trajectory, wherein the circular motion trajectory includes the target circular motion trajectory and the predicted circular motion trajectory; The instantaneous vibration circumferential locus of the bearing cage for wind power generation is obtained based on the vibration acceleration of the bearing cage for wind power generation, specifically, Obtaining vibration acceleration during a target period using a vibration sensor in the wind power generation unit; Using a quaternion parameter algorithm, perform quaternion differential division on the motion trend data in the target circular motion trajectory to obtain a motion posture matrix of the associated quaternion differential; Dividing the vibration acceleration during the target period into components in each axial direction in a three-dimensional space based on the movement posture matrix to obtain coordinate data of a vibration vector; performing transient fitting of a circumferential curve to the coordinate data of the vibration acceleration and the vibration vector to obtain a transient fitting curve; According to a three-dimensional space in which the wind power generation bearing cage is located, matching a corresponding position with respect to the transient fitting curve to determine an instantaneous vibration circumferential locus during the target period; The instantaneous vibration circular locus is used to perform irregular trajectory filtering processing on a target circular motion locus in the circular motion locus to obtain an ideal circular motion locus of the bearing cage for wind power generation, specifically, performing linear normalization processing on the instantaneous vibration circular trajectory and the target circular motion trajectory to obtain an instantaneous vibration circular curve and a target circular curve, respectively, wherein the instantaneous vibration circular curve and the target circular curve are both spiral circular curves; performing a differential process on the coordinate points corresponding to the instantaneous vibration circumferential curve and the target circumferential curve to obtain a distance between a plurality of coordinate points, and performing a median process on the distances between the plurality of coordinate points to obtain a vibration differential distance; performing curve correction on the target circumferential curve based on the vibration difference distance to obtain a corrected circumferential curve; and performing vector processing on the corrected circumferential curve based on acceleration data in the target circular motion trajectory to determine a corrected circular motion trajectory; and performing filter screening of irregular loci within a preset error range for the target circular motion locus using the corrected circular motion locus to obtain an ideal circular motion locus of the bearing cage for wind power generation. An ideal circumferential spatial region and a corresponding predicted circumferential spatial region are generated for the ideal circular motion trajectory and the predicted circular motion trajectory, respectively, and a positioning comparison of probability centers of gravity of spatial regions is performed for the ideal circumferential spatial region and the predicted circumferential spatial region to obtain a predicted overlap spatial region, specifically, generating a first spiral cylinder corresponding to the ideal circumferential space region and a second spiral cylinder corresponding to the predicted circumferential space region based on the ideal circumferential motion trajectory and the predicted circumferential motion trajectory, respectively, wherein the first spiral cylinder and the second spiral cylinder each include a plurality of point position information; Obtaining position information of a first point in the first helical cylinder; According to the significance of the probability distribution function, obtain a point distribution planar area corresponding to the first point position information, and use the probability density function to position the centroid of a spiral cylinder relative to the point distribution planar area to obtain first centroid position information of the first spiral cylinder; locating a centroid of an associated point distribution planar region with respect to the second helical cylinder to obtain second centroid position information of the second helical cylinder; performing overlap matching of the first spiral cylinder and the second spiral cylinder in a three-dimensional space of the same time domain and the same space domain based on the first centroid position information and the second centroid position information, to determine a predicted overlap space domain where the first spiral cylinder and the second spiral cylinder overlap each other; Based on the predicted overlap space area, it is determined whether there is an abnormality in the operating condition of the bearing cage for wind power generation, and operation monitoring information for the bearing for wind power generation is obtained, specifically, Determining a third helical cylinder of an associated actual circumferential space region based on an actual circumferential motion trajectory corresponding to a next period, wherein the actual circumferential motion trajectory is a point circumferential motion trajectory of a next period from the ideal circumferential motion trajectory; locating a centroid of an associated point distribution planar region with respect to the third spiral cylinder to obtain third centroid position information of the third spiral cylinder; Based on the third centroid position information, perform overlap matching of the first spiral cylinder and the third spiral cylinder in three-dimensional space in the same time domain and the same space domain to obtain a true overlap space domain; and determining whether there is an abnormality in the operating status of the bearing cage for wind power generation based on spatial area size determination information between the true overlap spatial area and the predicted overlap spatial area, obtaining operation monitoring information for the wind power generation bearing, and completing operation monitoring of the wind power generation unit.

2. Determining the point tracking information of all the sensor chips from the secondary coordinate data and the target coordinate data of the first sensor chip specifically includes: According to a target period, performing weighted fusion of related coordinate data on the secondary coordinate data in the neighboring cluster head node and the primary coordinate data in the main cluster head node to obtain target coordinate data of the first sensor chip; Determine the signal transmitting node of the first sensor chip as an adjacent cluster head node based on a preset grid structure of a WSN, and determine the target coordinate data as adjacent coordinate data; After performing a minimum value process of the average spatial distance on the coordinate data of the fourth sensor chip and the target coordinate data of the first sensor chip, the target coordinate data of the second sensor chip is obtained by weighted fusion of the coordinate data, and the fourth sensor chip and the first sensor chip are both placed in positions adjacent to each other on the left and right of the second sensor chip; In this way, performing weighted fusion of the related coordinate data for all sensor chips to determine target coordinate data for all sensor chips respectively, and obtaining corresponding acceleration data for the plurality of sensor chips during the target period; and determining point tracking information of all the sensor chips from the target coordinate data and corresponding acceleration data of all the sensor chips.

3. at least one processor; a memory communicatively connected to the at least one processor; The memory stores instructions that can be executed by the at least one processor, thereby enabling the at least one processor to execute the operation monitoring method for a bearing cage for wind power generation according to claim 1 or 2.

Images