Method and apparatus for monitoring operation of bearing retainer 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] This application relates to the field of data monitoring and prediction, and particularly to a method and device for monitoring the operation of a bearing retainer for wind power generation.

Background Art

[0002] As a kind of green energy, wind power generation has been developing at an unimaginable speed since the 1980s. With the increasing maturity of related technologies, it has already become a widely used new energy power generation method. Since the wind power generation unit operates under complex alternating loads for a long time, the requirements for the transmission system of wind power generation are becoming increasingly strict. As an important component of the wind power generation unit, the bearing plays an extremely important role in ensuring the reliability of the whole unit.

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

[0004] However, the above monitoring method using a vibration sensor is difficult to monitor the operating characteristic quantities of specific operating conditions of the wind power generation bearing or the bearing retainer for wind power generation, and there is a certain delay. Generally, it is not until a failure occurs and intense vibration occurs that it is finally monitored. Moreover, the location of the wind power generation device is generally remote, and the maintenance interval is very long, which will cause irreparable losses to the wind power generation unit, blades, hub, etc., and easily result in waste of a lot of resources. In addition, it is difficult to perform real-time online monitoring and prediction on the operating state of the wind power generation main shaft, and it is impossible to feedback to the maintenance staff in a timely and predictive manner, which will increase the operation and maintenance costs of the wind power generation unit.

Summary of the Invention

Problems to be Solved by the Invention

[0005] In the embodiments of the present application, it is difficult to perform real-time online monitoring and prediction on the operating status of conventional wind power units, and there is also a certain delay in the fault reports of wind power units. Therefore, it is disadvantageous for quickly maintaining abnormal wind power units, and the maintenance cost will increase significantly. To solve the technical problem, a method and device for monitoring the operation of a bearing retainer for wind power generation are provided.

Means for Solving the Problems

[0006] The embodiments of the present application use the following technical means. In one aspect of the present application, the embodiments of the present application are a plurality of sensor chips pre - provided in a bearing retainer for wind power generation, which perform multi - point multi - cluster head assisted tracking on the operating state of the bearing retainer for wind power generation to obtain point tracking information. The point tracking information includes the target coordinate data and corresponding acceleration data of all sensor chips in any period. Orthogonal coverage of points is performed on the point tracking information, and motion vector correction and prediction of related points are performed on the point tracking information after orthogonal coverage to obtain the circular motion trajectory of the points. The circular motion trajectory includes a target circular motion trajectory and a predicted circular motion trajectory. Based on the vibration acceleration of the bearing retainer for wind power generation, the instantaneous vibration circular trajectory of the bearing retainer for wind power generation is obtained. By using the instantaneous vibration circular trajectory, filtering processing of irregular trajectories is performed on the target circular motion trajectory in the circular motion trajectory to obtain the ideal circular motion trajectory of the bearing retainer for wind power generation. Corresponding ideal circular space regions and corresponding predicted circular space regions are respectively generated for the ideal circular motion trajectory and the predicted circular motion trajectory. Positioning and comparison of the probability centroids of the space regions are performed on the ideal circular space region and the predicted circular space region to obtain a predicted overlapping space region. Based on the predicted overlapping space region, it is determined whether there is an abnormality in the operating condition of the bearing retainer for wind power generation, and the operating monitoring information of the wind power bearing is obtained to complete the operating monitoring of the wind power unit. A method for monitoring the operation of a bearing retainer for wind power generation is provided.

[0007] The beneficial effects of the present application are as follows. By monitoring the operating trajectory of the bearing cage for wind power in the wind power main bearing, based on the error comparison between the predicted overlapping space area and the actual overlapping space area, it can be monitored in real time that there is actually an abnormal operating condition in the bearing cage for wind power. Furthermore, it is possible to predict whether there are abnormal conditions in the wind power main shaft and the wind power unit, which can timely feedback the potential fault problems to the maintenance staff, and let them arrive at the site immediately, which helps to prevent the progress of potential faults. It is helpful to conduct real-time online monitoring and prediction of the operating condition of the wind power unit, shorten the delay time of reporting potential faults of the wind power unit, help to promptly maintain the abnormal wind power unit, reduce the maintenance cost, and guarantee the normal power generation efficiency of the wind power unit.

[0008] In a possible embodiment, multiple sensor chips pre - provided in a bearing retainer for wind power generation perform multi - point multi - cluster head assisted tracking on the operating state of the bearing retainer for wind power generation to obtain point - tracking information. Specifically, it is to collect signals from the multiple sensor chips in the bearing retainer for wind power generation by a signal collection device in a wind power generation unit to determine whether the bearing retainer for wind power generation is operating. The multiple sensor chips are embedded in the bearing retainer for wind power generation, evenly distributed, and adapted to the rotational balance of the bearing retainer for wind power generation. When the bearing retainer for wind power generation is operating, determine the signal - transmitting node of the first sensor chip during operation as the 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. The second sensor chip and the third sensor chip are respectively located at positions adjacent to the left and right of the first sensor chip. Based on a preset RSSI algorithm, calculate the three - dimensional space distance of the related received signal carrier power for the preset period for the main cluster head node and the adjacent cluster head nodes respectively to obtain the main coordinate data and adjacent coordinate data within the target period. Both the main coordinate data and the adjacent coordinate data are three - dimensional coordinate data. Based on the least - squares algorithm, perform a minimum - value processing on the average space distance for the adjacent coordinate data within the target period, calculate the median related to the space distance after the minimum - value processing to obtain the secondary coordinate data, and determine 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 a bearing retainer for wind power generation monitor the operating conditions of a two-row self-aligning spherical roller bearing in real time, that is, can track in real time by points the operating postures and trajectories in the three-dimensional space of the bearing retainer for wind power generation, and based on the cooperative fusion of multi-cluster heads, the adjacent chips of each sensor chip realize the real-time tracking of each sensor chip to obtain the principal coordinate data and adjacent coordinate data within the target period.

[0010] In a possible embodiment, determining the point tracking information of all sensor chips from the secondary coordinate data and the target coordinate data of the first sensor chip specifically includes, according to the target period, performing weighted fusion of the coordinate data related to the secondary coordinate data in the adjacent cluster head nodes and the principal coordinate data in the main cluster head nodes to obtain the target coordinate data of the first sensor chip; determining the signal transmission node of the first sensor chip as an adjacent cluster head node based on the preset grid structure of the WSN and determining the target coordinate data as adjacent coordinate data; after performing the minimum value processing of the average spatial distance on the coordinate data of the fourth sensor chip and the target coordinate data of the first sensor chip, obtaining the target coordinate data of the second sensor chip by weighted fusion of the coordinate data, where the fourth sensor chip and the first sensor chip are both placed at positions adjacent to the left and right of the second sensor chip; and in this way, performing weighted fusion of the coordinate data related to all sensor chips to respectively determine the target coordinate data of all sensor chips, obtaining the corresponding acceleration data of the plurality of sensor chips during the target period; and determining the point tracking information of all sensor chips from the target coordinate data and the corresponding acceleration data of all sensor chips.

[0011] The beneficial effects of the present application are as follows. The adjacent cluster head nodes are fused into the main cluster head node to achieve weighted fusion of the secondary coordinates and the main coordinates, which is based on the adjacent secondary cluster head nodes to achieve target tracking for the main cluster head node, that is, it helps to achieve tracking for the first sensor chip, and finally obtain the coordinate data and corresponding acceleration data of the relevant first sensor chip. In this way, the point tracking information of the second, third, fourth, etc. sensor chips is obtained respectively, and the point tracking of all sensor chips in the bearing retainer for wind power generation is realized.

[0012] In a possible embodiment, performing point orthogonal coverage on the point tracking information specifically includes: performing point sampling on the target coordinate data corresponding to each sensor chip in the point tracking information during the target period by means of an orthogonal coverage mechanism to obtain the multi-point position data of the relevant target coordinate data; dividing it as the sampling space region corresponding to the point sampling based on the multi-point position data; determining the relevant signal strength for the multi-point position data according to the sampling space region to obtain the signal strength numbers of the relevant multi-points; judging the motion trend for the multi-point position data based on the signal strength numbers and the point density in the sampling space region, using the point with the maximum signal strength in the signal strength numbers as the reference point to determine the motion trend data of the points during the target period; acquiring the acceleration data corresponding to each sensor chip in the point tracking signal, and based on the motion trend data of the points, making the acceleration data and the multi-point position data in the sampling space region correspond one-to-one to generate the target circular motion trajectory from the point tracking information.

[0013] The beneficial effects of the present application are as follows. Based on the point tracking information of each sensor chip, the sampling space area during the target period is determined, and different signal strength numbers are formed from the distance differences of each sensor chip distance signal collection device within the sampling space area, which helps to further determine the movement trends of multiple points in the target sampling space area based on the signal strength numbers, the point density, and the point positions in the sampling space. Then, in combination with the acceleration of each point, the final target circular motion trajectory is formed.

[0014] In a possible embodiment, performing related point motion vector correction and prediction on the point tracking information after orthogonal coverage to obtain the circular motion trajectory of the point specifically includes: obtaining the point tracking information after orthogonal coverage during the target period; based on the Lagrange interpolation function, performing vector prediction of the coordinate positions in the next period for the target coordinate data in the target circular motion trajectory from the acceleration data in the target circular motion trajectory to obtain predicted target coordinate data; based on the positioning distances between each point in the target circular motion trajectory, performing vector prediction of the acceleration in the next period for the acceleration data in the target circular motion trajectory to obtain predicted acceleration data; sampling predicted points for the predicted target coordinate data and dividing them as the predicted sampling space area corresponding to the predicted target coordinate data; determining the predicted motion trends for multiple points in the predicted sampling space area based on the signal strength numbers of the predicted points and the corresponding predicted point densities in the predicted sampling space area; generating the predicted circular motion trajectory in the next period based on the predicted points and the corresponding predicted acceleration data in the predicted sampling space area; 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. By means of the Lagrange difference function, the coordinate data and acceleration data of all points within the next period can be further predicted, 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 a possible embodiment, obtaining the instantaneous vibration circular trajectory of the bearing cage for wind power generation based on the vibration acceleration of the bearing cage for wind power generation specifically includes: using a vibration sensor in the wind power generation unit to obtain the vibration acceleration within the target period; performing quaternion differential division on the motion trend data in the target circular motion trajectory by means of the quaternion parameter algorithm to obtain the operation attitude matrix of the related quaternion differential; based on the operation attitude matrix, dividing the vibration acceleration within the target period into components in each axial direction in the three-dimensional space to obtain the coordinate data of the vibration vector; performing transient fitting of a circular curve on the vibration acceleration and the coordinate data of the vibration vector to obtain a transient fitting curve; and performing matching of the corresponding positions on the transient fitting curve according to the three-dimensional space where the bearing cage for wind power generation is located to determine the instantaneous vibration circular trajectory within the target period.

[0017] The beneficial effects of the present application are as follows. Using a vibration sensor pre-provided in the wind power generation unit, the obtained vibration acceleration is divided into each axial direction, and then transient fitting of a curve is performed on the vibration vector data to obtain the instantaneous vibration circular trajectory of the related vibration acceleration, thereby accurately recognizing the offset amount generated from the vibration of the impeller load and obtaining the instantaneous vibration circular trajectory of the bearing cage for wind power generation in the state of the offset amount.

[0018] In a possible embodiment, by means of the instantaneous vibration circular trajectory, filtering processing of an irregular trajectory with respect to a target circular motion trajectory in the circular motion trajectory is performed to obtain an ideal circular motion trajectory of the bearing retainer for wind power generation. Specifically, linear normalization processing 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 respectively. Both the instantaneous vibration circular curve and the target circular curve are spiral circular curves. Difference processing of corresponding coordinate points is performed on the instantaneous vibration circular curve and the target circular curve to obtain distances of a plurality of coordinate points. Median processing is performed on the distances of the plurality of coordinate points to obtain a vibration difference distance. Based on the vibration difference distance, curve correction is 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. By means of the corrected circular motion trajectory, filtering screening of an irregular trajectory is performed within a preset error range with respect to the target circular motion trajectory to obtain an ideal circular motion trajectory of the bearing retainer for wind power generation.

[0019] The beneficial effects of the present application are as follows. By means of the recognized instantaneous vibration circular trajectory, errors with respect to the target circular motion trajectory are corrected, and corresponding corrections to the target circular curve are timely performed based on the vibration difference distance, thereby accurately obtaining the true operating conditions inside the wind power generation unit, that is, the true circular motion trajectory of the bearing retainer for wind power generation.

[0020] In a possible embodiment, an ideal circumferential space region and a corresponding predicted circumferential space region corresponding to the ideal circumferential motion trajectory and the predicted circumferential motion trajectory are respectively generated, and a positioning comparison of the probability center of gravity of the space region is performed on the ideal circumferential space region and the predicted circumferential space region to obtain a predicted overlapping space region. Specifically, based on the ideal circumferential motion trajectory and the predicted circumferential motion trajectory, a first helical cylinder corresponding to the ideal circumferential space region and a second helical cylinder corresponding to the predicted circumferential space region are respectively generated. Both the first helical cylinder and the second helical cylinder include a plurality of point position information. Obtaining the first point position information in the first helical cylinder, obtaining a point distribution plane region corresponding to the first point position information based on the significance of the probability distribution function, positioning the center of gravity of the helical cylinder with respect to the point distribution plane region by the probability density function to obtain the first center of gravity position information of the first helical cylinder, positioning the center of gravity of the point distribution plane region related to the second helical cylinder to obtain the second center of gravity position information of the second helical cylinder, and based on the first center of gravity position information and the second center of gravity position information, performing an overlapping comparison of the three-dimensional space in the same time region and the same space region for the first helical cylinder and the second helical cylinder to determine a predicted overlapping space region that overlaps with the first helical cylinder and the second helical cylinder.

[0021] The beneficial effects of the present application are as follows. Based on the circumferential motion trajectory in the three-dimensional space in each period, a motion trajectory quantity with a time component, that is, a helical cylinder, is constructed. Next, based on the center of gravity position, an overlapping comparison is performed on the space regions where the helical cylinders in different periods are located to obtain a predicted overlapping region, which is useful for monitoring the operation of the bearing retainer for wind power generation and predicting the overlapping situation of the space regions within different periods in a normal state.

[0022] In one possible embodiment, based on the predicted overlapping spatial region, determining whether there is an abnormality in the operating condition of the bearing retainer for wind power generation to obtain the operation monitoring information of the wind power bearing specifically includes: determining a third helical cylinder of the relevant actual circumferential spatial region based on the actual circumferential motion trajectory corresponding to the next period, where the actual circumferential motion trajectory is the point circumferential motion trajectory of the next period from the ideal circumferential motion trajectory; positioning the centroid of the relevant point distribution plane region with respect to the third helical cylinder to obtain the third centroid position information of the third helical cylinder; performing three-dimensional space overlapping comparison of the first helical cylinder and the third helical cylinder in the same time region and the same space region based on the third centroid position information to obtain the true overlapping spatial region; and determining whether there is an abnormality in the operating condition of the bearing retainer for wind power generation based on the size determination information of the spatial regions of the true overlapping spatial region and the predicted overlapping spatial region, obtaining the operation monitoring information of the wind power bearing, and completing the operation monitoring of the wind power unit.

[0023] In another aspect, an embodiment of the present application further includes at least one processor and a memory communicatively connected to the at least one processor, where instructions executable by the at least one processor are stored in the memory, whereby the at least one processor can execute the operation monitoring method of the bearing retainer for wind power generation described in any of the above embodiments, and provides an operation monitoring device for the bearing retainer for wind power generation.

[0024] The beneficial effects of the present application are as follows. By monitoring the operating trajectory of the bearing cage for wind power generation in the wind power main bearing, based on the error comparison between the predicted overlapping spatial region and the actual overlapping spatial region, it can be monitored in real time that there is actually an abnormal operating condition in the bearing cage for wind power generation. Furthermore, it is possible to predict whether there are abnormal conditions in the wind power main shaft and the wind power unit. This feeds back potential fault problems to maintenance staff in a timely manner and enables them to arrive at the site immediately, which helps to prevent the progression of potential faults. It is useful for real-time online monitoring and prediction of the operating conditions of the wind power unit, shortens the delay time for reporting potential faults of the wind power unit, helps to promptly maintain the abnormal wind power unit, reduces the maintenance cost, and guarantees the normal power generation efficiency of the wind power unit.

Brief Description of the Drawings

[0025] To more clearly explain the technical means according to the embodiments or the prior art of the present application, the following briefly introduces the drawings to be used in the description of the embodiments or the prior art. Needless to say, the drawings in the following description are only some embodiments described in the present application, and those skilled in the art can also obtain other drawings based on these drawings without performing creative work. In the drawings,

[0026]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Embodiments for Carrying out the Invention

[0027] To enable those skilled in the art to better understand the technical means of the present application, the following refers to the drawings of the embodiments of the present application to clearly and completely describe the technical means of the embodiments of the present application. Needless to say, the described embodiments are only a part of the embodiments of the present application, not all embodiments. All other embodiments obtained by those skilled in the art from the embodiments of this specification without performing inventive work shall fall within the protection scope of the present application.

[0028] The embodiment of the present application provides an operation monitoring method for a bearing retainer for wind power generation. As shown in FIG. 1, the operation monitoring method for a bearing retainer for wind power generation specifically includes steps S101 to S106. Note that the wind power generation transmission main shaft of the wind power generation unit in the wind power generation device is provided with two wind power generation bearings, and generally a two-row self-aligning spherical roller bearing is used. Optionally, for example, FIG. 2 is a structural schematic diagram of a two-row self-aligning spherical roller bearing provided by an embodiment of the present application. As shown in FIG. 2, the self-aligning spherical roller bearing is provided with two rows of rollers and is fixed and held by a bearing retainer. During the operation of the wind power generation unit, a certain load pressure is applied to the main shaft, so the center of gravity of the main shaft is offset. Therefore, due to the characteristics of the self-aligning spherical roller bearing, a certain offset can be realized on the main shaft. The bearing retainer for wind power generation moves offset to a certain extent according to the offset of the main shaft, that is, there is not only horizontal rotation but also offset at each direction angle. Therefore, by monitoring the movement trajectory of the bearing retainer for wind power generation, the operation monitoring of the wind power generation bearing is realized, which can further reflect the operation status of the wind power generation main shaft and the operation status of the entire wind power generation unit.

[0029] In S101, multiple sensor chips pre - provided in the bearing retainer for wind power generation perform multi - point multi - cluster head assisted tracking on the operating state of the bearing retainer for wind power generation to obtain point tracking information. The point tracking information includes the target coordinate data and corresponding acceleration data of all sensor chips in any period.

[0030] Specifically, a signal collection device in the wind power generation unit collects signals from multiple sensor chips in the bearing retainer for wind power generation to determine whether the bearing retainer for wind power generation is operating. The multiple sensor chips are embedded in the bearing retainer for wind power generation, evenly distributed, and adapted to the rotational balance of the bearing retainer for wind power generation. When the bearing retainer for wind power generation is operating, the signal transmission node of the first sensor chip during operation is determined as the main cluster head node, and the signal transmission 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 at positions adjacent to the left and right of the first sensor chip.

[0031] In one embodiment, FIG. 4 is a schematic diagram of the sensor chip distribution of the bearing retainer for wind power generation provided by the embodiment of the present application. As shown in FIG. 4, when manufacturing a bearing retainer for wind power generation adapted to a two - row self - aligning spherical roller bearing, several sensor chips are placed into the bearing retainer for wind power generation by a pressing process or an integrated manufacturing process and evenly distributed inside the retainer, so that the retainer meets the requirements of dynamic balance during operation and ensures the normal and stable operation of the retainer. According to the arrangement method shown in FIG. 4, eight sensor chips are arranged one by one in sequence on both the left and right sides. Also, the sensor chip has a signal transmission function for transmitting real - time coordinate data and acceleration data, whereby the signal collection device collects the transmitted signals.

[0032] In one embodiment, FIG. 3 is a structural schematic diagram of the operation monitoring for the wind power bearing provided by the embodiment of the present application. As shown in FIG. 3, a signal server connected to the signal collection device in the wind power unit performs multi-point multi-cluster head assisted tracking on the operating wind power bearing retainer. Further, different levels of cluster heads are used to improve the positioning and tracking accuracy of the sensor chip, reduce the target loss rate of the points, and complete different tasks at different stages in order to divide the cluster heads into main cluster head nodes and secondary cluster head nodes.

[0033] Furthermore, based on a preset RSSI (Received Signal Strength Indicator) algorithm, the three-dimensional spatial distances of the related received signal carrier powers for the main cluster head node and the adjacent cluster head node are calculated respectively according to a preset period, and the main coordinate data and the adjacent coordinate data within the target period are obtained respectively. The main coordinate data and the adjacent coordinate data are both three-dimensional coordinate data.

[0034] In one embodiment, a signal receiving device calculates the relative distances of the received signal carrier powers for the determined main cluster head node and adjacent cluster head node based on the RSSI algorithm, 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). In the formula, α, β, γ are coordinate reference intermediate quantities, P0 is the reference signal carrier power, P y , P x , P z are the carrier powers in the y, x, z axis directions respectively, d0 is the preset reference signal reception distance, and then the main coordinate data and the adjacent coordinate data within the target period are determined respectively.

[0035] Furthermore, based on the least-squares algorithm, the minimum value processing of the average spatial distance is performed on the adjacent coordinate data within the target period, and the median related to the spatial distance after the minimum value processing is calculated to obtain the quadratic coordinate data.

[0036] In one embodiment, matrix display by multi-lateration is performed on two adjacent coordinate data within the target period to obtain the matrix A of the related second sensor chip and the matrix B corresponding to the third sensor chip respectively. Since there may be ranging errors, a random error vector is added and combined with the least-squares algorithm to perform the minimum value processing on the average spatial distance between matrix A and matrix B. Next, median differentiation is performed on the average spatial distance after the minimum value processing, and finally, the quadratic coordinate data in which two adjacent coordinates map to each other is obtained.

[0037] Furthermore, based on the target period, weighted fusion of the coordinate data related to the quadratic coordinate data in the adjacent cluster head nodes and the main coordinate data in the main cluster head nodes is performed to obtain the target coordinate data of the first sensor chip.

[0038] As a possible embodiment, the quadratic coordinate data in the adjacent cluster head nodes is sent to the main cluster head node. Next, from the difference in the proportions occupied by the weights of the quadratic coordinate data and the main coordinate data, the two are divided without weights, that is, the quadratic coordinate data is fused with the main coordinate data, thereby reducing the tracking positioning error generated 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, in this way, based on the preset grid structure of the WSN (Wireless Sensor Network), first, the signal transmission node of the first sensor chip is determined as the adjacent cluster head node, and the target coordinate data is determined as the adjacent coordinate data. After performing the minimum value processing 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. The fourth sensor chip and the first sensor chip are both placed at positions adjacent to the left and right of the second sensor chip. In this way, weighted fusion of the relevant coordinate data is performed on all the sensor chips to determine the target coordinate data of all the sensor chips respectively. The corresponding acceleration data during the target period of the plurality of sensor chips is acquired. Next, the point tracking information of all the sensor chips is finally determined from the target coordinate data and the corresponding acceleration data of all the sensor chips.

[0040] As a possible embodiment, as shown in FIG. 4, following the point tracking of the first sensor chip, the point tracking of the remaining sensors is performed in sequence. In this way, the second sensor chip, the third sensor chip, the fourth sensor chip, etc. are respectively determined as the main cluster head nodes in this order, the corresponding adjacent sensor chips are determined as the adjacent cluster head nodes in sequence, and finally the target coordinate data of each sensor chip is obtained. Then, according to the period in which each sensor chip is located, the acceleration data during the corresponding period of each sensor chip is acquired, and finally the acceleration data and the target coordinate data of each sensor chip are determined as the point tracking information of the point where the sensor chip is located.

[0041] S102 is to perform point orthogonal coverage on the point tracking information. Perform the movement vector correction and prediction of the relevant points on the point tracking information after the orthogonal coverage to obtain the circular motion trajectory of the point. The circular motion trajectory includes the target circular motion trajectory and the predicted circular motion trajectory.

[0042] Specifically, by means of an orthogonal coverage mechanism, point sampling is performed on the target coordinate data corresponding to each sensor chip in the point tracking information for the target period to obtain the multi-point position data of the relevant target coordinate data. Further, based on the multi-point position data, it is divided into a sampling space region corresponding to the point sampling.

[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. Next, orthogonal coverage is performed on the above two points, that is, sample point 1 (X1, Y1, Z1) and sample point 2 (X2, Y2, Z2) based on the orthogonal mechanism. Further, X fin = βX1 + αX2, Y fin = βY1 + αY2, Z fin = βZ1 + αZ2, based on this, the multi-point position data, that is, the multi-point position coordinates (X fin , Y fin , Z fin ) in the position data are obtained. Next, based on these position data after sampling extraction, it is divided into a sampling space region corresponding to the sampling point. Here, α and β are intermediate quantities of orthogonal coverage.

[0044] Furthermore, by means of the sampling space region, the signal strength related to the multi-point position data is determined, and the signal strength number of the relevant multi-point is obtained. Further, based on the signal strength number and the point density in the sampling space region, the movement trend of the multi-point position data is judged. Taking the point with the maximum signal intensity in the signal strength number as the reference point, the movement trend data of the points in the target period is determined.

[0045] In one embodiment, P(N) = L((ε(d1 - d0) 2) Based on ( / μ), the signal strength related to the position data of the sampling region is judged to obtain the signal strength number P(N) of each point. L is the point density, μ is the sampling space region, d1 is the signal reception distance between the point and the signal collection device, d0 is the inherent error distance, ε is the signal frequency parameter. Next, based on the signal strength number of each point, a corresponding mark is made for each point. Then, based on the mark number, the movement trend of the multi-point position data is judged. Taking the point with the maximum signal intensity as the reference point, finally, the movement trend data of the points in the target period is determined.

[0046] Furthermore, first, the acceleration data corresponding to each sensor chip in the point tracking signal is obtained. Based on the movement trend data of the points, the acceleration data and the position data of the multi-points in the sampling space region are made to correspond one-to-one to generate the target circular motion trajectory from the point tracking information.

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

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

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

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

[0051] In one example, from the limit value d i in the orthogonal coverage of each node in the target circular motion trajectory in the sampling space region, next R i=min(r, d i ) Based on this, the positioning distance R between each point in the target circular motion trajectory i is obtained. In the formula, r is the reference radius distance of each node. Furthermore, using the Lagrange interpolation function L(i) in the target k period, a vector prediction of the acceleration in the k + 1 period is performed on the acceleration data in the target circular motion trajectory, and the predicted velocity in the k + 1 period of the acceleration vectors in each axis direction, that is, the x-axis, y-axis, and z-axis, is obtained. Next, after vectorially adding the velocities in the three axis directions, the acceleration data of each point in the k + 1 period is obtained. Here, the x-axis and y-axis are the coordinate axes in the same plane of the roller, and the z-axis is the direction of the main axis of the wind power generation.

[0052] Furthermore, based on the signal strength numbers of the predicted points and the corresponding predicted point densities in the predicted sampling space region, the predicted motion trends of the multi-points in the predicted sampling space region are judged. After matching the predicted acceleration data with the predicted points in the predicted sampling space region, the predicted circular motion trajectory for the next period is generated. From the predicted circular motion trajectory and the target circular motion trajectory, the circular motion trajectory of the points is obtained.

[0053] As a possible embodiment, after obtaining the predicted target coordinate data and the corresponding acceleration data, point sampling is performed on the predicted target coordinate data corresponding to each sensor chip in the predicted point tracking information for the next period to obtain the position data of the predicted multi-points of the relevant predicted target coordinate data. Furthermore, based on the position data of the predicted multi-points, it is divided into a predicted sampling space region corresponding to the point sampling. The relevant signal strength is determined for the position data of the predicted multi-points by the predicted sampling space region, and the signal strength numbers of the relevant predicted multi-points are obtained. Furthermore, based on the signal strength numbers and the point density in the predicted sampling space region, the predicted motion trend of the position data of the multi-points is judged. After matching the predicted acceleration data obtained above with the predicted points in the predicted sampling space region, the predicted circular motion trajectory for the next period is generated.

[0054] In S103, based on the vibration acceleration of the bearing retainer for wind power generation, obtain the instantaneous vibration circular trajectory of the bearing retainer for wind power generation.

[0055] Specifically, first, use the vibration sensor in the wind power generation unit to obtain the vibration acceleration during the target period. Further, by the quaternion parameter algorithm, perform quaternion differential division on the motion trend data in the target circular motion trajectory to obtain the operation attitude matrix of the related quaternion differential.

[0056] Furthermore, based on the operation attitude matrix, divide the components in each axis direction in the three-dimensional space for the vibration acceleration during the target period to obtain the coordinate data of the vibration vector. Next, perform transient fitting of the circular curve on the vibration acceleration and the coordinate data of the vibration vector to obtain the transient fitting curve.

[0057] Furthermore, according to the three-dimensional space where the bearing retainer for wind power generation is located, then perform matching of the corresponding positions on the transient fitting curve to determine the instantaneous vibration circular trajectory during the target period.

[0058] In one embodiment, first, use the vibration sensor in the wind power generation unit to obtain the vibration acceleration during the target period. First, based on the conversion relationship between the absolute coordinate and the relative coordinate, and further use quaternions to perform coordinate conversion on the motion trend data in the target circular motion trajectory, that is, perform data conversion between the target coordinate data and the acceleration data of each point to generate a quaternion differential equation. Next, perform matrix conversion on the quaternion differential equation to generate the operation attitude matrix of the related quaternion differential.

[0059] In one embodiment, from the quaternion parameters in the motion posture matrix, the components of the vibration acceleration in the target period are divided in the x-axis, y-axis, and z-axis directions to generate a vibration acceleration component matrix in the relevant axis directions. Next, through an integration operation, a transient fitting is performed on the vibration acceleration component matrix for the relevant circular curve to obtain a transient fitting curve. Then, for the transient fitting curve and the three-dimensional space where the target circular motion trajectory is located, in the same period, by matching each corresponding point one by one, the transient fitting curve and the target circular motion trajectory are positioned in the circular space region in the same time and space. Next, from the corresponding vibration acceleration and the transient fitting circular motion trajectory, the instantaneous vibration circular trajectory in the target period is determined.

[0060] This is S104, in which, based on the instantaneous vibration circular trajectory, a filtering process is performed on the irregular trajectory with respect to the target circular motion trajectory in the circular motion trajectory to obtain an ideal circular motion trajectory of the bearing retainer for wind power generation.

[0061] Specifically, 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 respectively. Both the instantaneous vibration circular curve and the target circular curve are spiral circular curves.

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

[0063] Furthermore, based on the vibration difference distance, next, a curve correction is performed on the target circular curve to obtain a corrected circular curve. Based on the acceleration data in the target circular motion trajectory, a vector process is performed on the corrected circular curve to determine a corrected circular motion trajectory. Subsequently, based on the corrected circular motion trajectory, a filtering screening of the irregular trajectory is performed within a preset error range with respect to the target circular motion trajectory to obtain an ideal circular motion trajectory of the bearing retainer for wind power generation.

[0064] In one embodiment, first, for preparation of comparative calculation, linear normalization processing is performed on the instantaneous vibration circumferential locus and the target circumferential motion locus so as to obtain an instantaneous vibration circumferential curve and a target circumferential curve. Next, the difference between the corresponding coordinate points of the instantaneous vibration circumferential curve and the target circumferential curve is obtained to determine the vibration differential distance of each point, thereby assisting in eliminating vibration from the target circumferential curve, ensuring the uniformity and completeness of the target circumferential curve. Then, by means of the corrected circumferential motion locus, filtering screening of irregular loci is performed within a preset error range with respect to the target circumferential motion locus to obtain an ideal circumferential motion locus of the bearing retainer for wind power generation.

[0065] S105, which is to respectively generate a corresponding ideal circumferential space region and a corresponding predicted circumferential space region for the ideal circumferential motion locus and the predicted circumferential motion locus. Positioning and collating of the probability centroids of the space regions are performed on the ideal circumferential space region and the predicted circumferential space region to obtain a predicted overlapping space region.

[0066] Specifically, based on the ideal circumferential motion locus and the predicted circumferential motion locus, a first helical cylinder corresponding to the ideal circumferential space region and a second helical cylinder corresponding to the predicted circumferential space region are respectively generated. Both the first helical cylinder and the second helical cylinder include a plurality of point position information.

[0067] Furthermore, the first point position information in the first helical cylinder is acquired. Next, based on the significance of the probability distribution function, a point distribution plane region corresponding to the first point position information is acquired. By means of the probability density function, the centroid of the helical cylinder is positioned with respect to the point distribution plane region to obtain the first centroid position information of the first helical cylinder. Subsequently, the centroid of the point distribution plane region related to the second helical cylinder is positioned to obtain the second centroid position information of the second helical cylinder.

[0068] Furthermore, based on the first centroid position information and the second centroid position information, three-dimensional space overlapping collation of the same time region and the same space region is performed on the first helical cylinder and the second helical cylinder to determine a predicted overlapping space region that overlaps with the first helical cylinder and the second helical cylinder.

[0069] In one embodiment, based on the data display status in the three-dimensional space of the ideal circular motion trajectory and the predicted circular motion trajectory, a first helical cylinder corresponding to the ideal circular space region and a second helical cylinder corresponding to the predicted circular space region are respectively generated. Here, both the spatial position and the helical angle of the helical cylinder are different depending on the period. Next, according to the significance of the probability distribution function, the significance of the first point position information in the first helical cylinder is recognized. Next, the point distribution plane region corresponding to the first point position information is obtained. Next, according to the probability density function, the centroid of the helical cylinder is positioned with respect to the point distribution plane region, and the centroid position data of the first helical cylinder is recognized to obtain the first centroid position information of the first helical cylinder. In this way, subsequently, the centroid of the relevant point distribution plane region is positioned with respect to the second helical cylinder, the centroid position data of the second helical cylinder is recognized, and finally the second centroid position information of the second helical cylinder is obtained.

[0070] As a possible embodiment, based on the first centroid position information and the second centroid position information, corresponding movement processing of the helical cylinders is performed in the three-dimensional space of the same time region and the same space region for the first helical cylinder and the second helical cylinder. Next, based on each corresponding point position, the spatial volumes of the first helical cylinder and the second helical cylinder are superimposed. Next, the trajectory portion of the same circular trajectory between the ideal circular motion trajectory and the predicted circular motion trajectory is recognized, and a predicted overlapping space region overlapping with each other between the first helical cylinder and the second helical cylinder is determined so as to remove the trajectory portions of different circular trajectories.

[0071] This is S106. Based on the predicted overlapping space region, it is determined whether there is an abnormality in the operating status of the bearing retainer for wind power generation, the operating monitoring information of the wind power bearing is obtained, and the operating monitoring of the wind power unit is completed.

[0072] Specifically, based on the actual circular motion trajectory corresponding to the next period, a third helical cylinder of the relevant actual circular space region is determined. 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 point distribution plane region related to the third helical cylinder is positioned to obtain the third centroid position information of the third helical cylinder.

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

[0075] Furthermore, based on the size determination information of the space regions of the true overlap space region and the predicted overlap space region, it is determined whether there is an abnormality in the operating status of the bearing retainer for wind power generation, and the operating monitoring information of the wind power bearing is obtained to complete the operating monitoring of the wind power unit.

[0076] In one embodiment, first, the corresponding actual circumferential motion trajectory in the next period is obtained, and the third helical cylinder of the related actual circumferential space region, that is, the helical cylinder corresponding to the motion trajectory of the bearing retainer for wind power generation in the next period is constructed. Next, the spatial volume collation is performed on the related center of gravity position information for the third helical cylinder and the first helical cylinder in the target period, so as to obtain the true overlapping space region between the first helical cylinder and the third helical cylinder, that is, the actual point circumferential motion trajectory of the bearing retainer for wind power generation from the target period to the next period. Next, the overlapping degree of the three-dimensional space in the same time region and space region is collated for the true overlapping space region and the predicted overlapping space region. The higher the overlapping degree, the more the operating condition of the bearing retainer for wind power generation conforms to the normal operating condition, that is, the operating condition of the wind power bearing conforms to the normal operating condition. Conversely, the lower the overlapping degree, the more the operating condition of the bearing retainer for wind power generation deviates from the normal operating condition, the more obvious the abnormal condition of the wind power bearing, and the more likely a potential failure occurs. Finally, the operation monitoring information of the wind power bearing is transmitted to the maintenance staff by the server in the wind power unit, so as to realize the real-time operation monitoring of the wind power unit. This can timely discover potential failures in abnormal operating conditions. If the maintenance staff makes a maintenance plan in advance, it can help prevent the expansion of the failure of the wind power unit and eliminate in advance the risk of potential abnormalities that may cause major failures.

[0077] In addition, the embodiment of the present application provides an operation monitoring device for a bearing retainer for wind power generation. As shown in FIG. 5, the operation monitoring device 500 for a bearing retainer for wind power generation specifically includes at least one processor 501 and a memory 502 communicably connected to the at least one processor. The memory 502 stores instructions executable by the at least one processor 501, whereby the at least one processor 501 With a plurality of sensor chips pre - provided in the bearing retainer for wind power generation, multi - point multi - cluster head - assisted tracking is performed on the operating state of the bearing retainer for wind power generation to obtain point - tracking information, where the point - tracking information includes the target coordinate data and corresponding acceleration data of all sensor chips in any period. Perform point orthogonal coverage on the point - tracking information, and perform movement vector correction and prediction on the relevant points of the point - tracking information after orthogonal coverage to obtain the circular motion trajectory of the points, where the circular motion trajectory includes the target circular motion trajectory and the predicted circular motion trajectory. Based on the vibration acceleration of the bearing retainer for wind power generation, obtain the instantaneous vibration circular trajectory of the bearing retainer for wind power generation. Perform filter processing on the irregular trajectories of the target circular motion trajectory in the circular motion trajectory according to the instantaneous vibration circular trajectory to obtain the ideal circular motion trajectory of the bearing retainer for wind power generation. Respectively generate the corresponding ideal circular space region and the corresponding predicted circular space region for the ideal circular motion trajectory and the predicted circular motion trajectory, and perform positioning and comparison of the probability centroids of the space regions on the ideal circular space region and the predicted circular space region to obtain the predicted overlapping space region. Based on the predicted overlapping space region, it is possible to judge whether there is an abnormality in the operating condition of the bearing retainer for wind power generation, obtain the operating monitoring information of the wind power bearing, and complete the operating monitoring of the wind power unit.

[0078] The beneficial effects of the present application are as follows. By monitoring the operating trajectory of the bearing cage for wind power generation in the wind power main bearing, based on the error comparison between the predicted overlapping spatial region and the actual overlapping spatial region, it is possible to monitor in real time that there was actually an abnormal operating condition in the bearing cage for wind power generation, and further predict whether there are abnormal conditions in the wind power main shaft and the wind power unit. This can timely feedback potential failure problems to the maintenance staff, and enable them to arrive at the site immediately, which helps to prevent the progress of potential failures. It is helpful for real-time online monitoring and prediction of the operating condition of the wind power unit, shortens the delay time of reporting potential failures of the wind power unit, helps to promptly maintain the abnormal wind power unit, reduces the maintenance cost, and guarantees the normal power generation efficiency of the wind power unit.

[0079] Each embodiment in the present application is described in a cascading manner, and the same or similar parts between each embodiment can be referred to each other. In the description of each embodiment, emphasis is placed on the parts different from other embodiments. In particular, in the case of embodiments of the device and the non-volatile computer storage medium, since they are similar to the embodiments of the method, they are described briefly, and the relevant parts can be referred to the description of the corresponding parts of the embodiments of the method.

[0080] Specific embodiments of the present application are described above. In some cases, the operations or steps described in the specification can still achieve the desired results even if they are executed in an order different from that of the embodiments. Also, the process depicted in the drawings does not necessarily have to be executed in the specific order or sequential order shown to achieve the desired results. In some embodiments, multitasking or parallel processing may also be possible or beneficial.

[0081] What is described above are only embodiments of the present application and are not intended to limit the present application. For those skilled in the art, various modifications and changes may exist in the embodiments of the present application. Any corrections, equivalent substitutions, improvements, etc. made within the spirit and principle of the embodiments of the present application shall be included within the scope of the specification of the present application.

Claims

1. A method for monitoring the operation of a bearing retainer for wind power generation, comprising: Performing multi-point multi-cluster head-assisted tracking on the operating state of the bearing retainer for wind power generation by a plurality of sensor chips previously provided in the bearing retainer for wind power generation to obtain point tracking information. Specifically, Collecting signals from a plurality of sensor chips in the bearing retainer for wind power generation by a signal collection device in a wind power unit to determine whether the bearing retainer for wind power generation is operating. The plurality of sensor chips are embedded in the bearing retainer for wind power generation, evenly distributed, and adapted to the rotational balance of the bearing retainer for wind power generation. When the bearing retainer for wind power generation is operating, determining the signal transmission node of the first sensor chip during operation as the main cluster head node, and determining the signal transmission nodes of the second sensor chip and the third sensor chip as adjacent cluster head nodes. The second sensor chip and the third sensor chip are respectively located at positions adjacent to the left and right of the first sensor chip. Calculating the three-dimensional space distance of the related received signal carrier power for the main cluster head node and the adjacent cluster head nodes respectively according to a preset RSSI algorithm within a preset period to obtain the main coordinate data and adjacent coordinate data within the target period. Both the main coordinate data and the adjacent coordinate data are three-dimensional coordinate data. Performing a minimum value process on the average space distance for the adjacent coordinate data within the target period based on the least squares algorithm, calculating the median related to the space distance after the minimum value process to obtain secondary coordinate data. Determining the 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 includes the target coordinate data and the corresponding acceleration data of all sensor chips in any period. Performing point orthogonal coverage on the point tracking information. Specifically, By means of the orthogonal coverage mechanism, perform point sampling on the target coordinate data corresponding to each sensor chip in the point tracking information during the target period to obtain the multi-point position data of the relevant target coordinate data, Based on the multi-point position data, divide it as a sampling space region corresponding to the point sampling, Use the sampling space region to determine the signal strength related to the multi-point position data and obtain the signal strength numbers of the relevant multi-points, Based on the signal strength numbers and the point density in the sampling space region, judge the movement trend of the multi-point position data. Using the point with the maximum signal intensity in the signal strength numbers as the reference point, determine the movement trend data of the points during the target period, Obtain the acceleration data corresponding to each sensor chip in the point tracking signal. Based on the movement trend data of the points, make the acceleration data correspond one-to-one with the position data of the multi-points in the sampling space region to generate the target circular motion trajectory from the point tracking information, including performing movement vector correction and prediction on the relevant points of the point tracking information after orthogonal coverage to obtain the circular motion trajectory of the points. Specifically, Obtain the point tracking information after orthogonal coverage during the target period, Based on the Lagrange interpolation function, perform vector prediction of the coordinate positions in the next period for the target coordinate data in the target circular motion trajectory from the acceleration data in the target circular motion trajectory to obtain the predicted target coordinate data, Based on the positioning distances between the points in the target circular motion trajectory, perform vector prediction of the acceleration in the next period for the acceleration data in the target circular motion trajectory to obtain the predicted acceleration data, Sample the predicted points for the predicted target coordinate data and divide it as the predicted sampling space region corresponding to the predicted target coordinate data, Based on the signal strength number of the prediction points and the corresponding prediction point density in the predicted sampling space region, determine the predicted motion trend for the multi-points in the predicted sampling space region, and generate the predicted circular motion trajectory for the next period based on the prediction points and the corresponding predicted acceleration data in the predicted sampling space region. Obtaining the circular motion trajectory of the point from the predicted circular motion trajectory and the target circular motion trajectory, where the circular motion trajectory includes the target circular motion trajectory and the predicted circular motion trajectory. Based on the vibration acceleration of the bearing retainer for wind power generation, obtain the instantaneous vibration circular trajectory of the bearing retainer for wind power generation. Specifically, Use a vibration sensor in the wind power generation unit to obtain the vibration acceleration during the target period. Perform quaternion differential division on the motion trend data in the target circular motion trajectory by the quaternion parameter algorithm to obtain the operation attitude matrix of the related quaternion differential. Based on the operation attitude matrix, divide the vibration acceleration in the target period into components in each axis direction in three-dimensional space to obtain the coordinate data of the vibration vector. Perform transient fitting of a circular curve on the vibration acceleration and the coordinate data of the vibration vector to obtain a transient fitting curve. Match the corresponding positions of the transient fitting curve according to the three-dimensional space where the bearing retainer for wind power generation is located to determine the instantaneous vibration circular trajectory during the target period. Perform filtering processing on the irregular trajectory of the target circular motion trajectory in the circular motion trajectory according to the instantaneous vibration circular trajectory to obtain the ideal circular motion trajectory of the bearing retainer for wind power generation. Specifically, Perform 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, where both the instantaneous vibration circular curve and the target circular curve are spiral circular curves. Perform difference processing on the corresponding coordinate points of the instantaneous vibration circular curve and the target circular curve to obtain the distances of a plurality of coordinate points, and perform median processing on the distances of the plurality of coordinate points to obtain a vibration difference distance. Based on the vibration differential distance, perform curve correction on the target circumferential curve to obtain a corrected circumferential curve, and based on the acceleration data in the target circumferential motion trajectory, perform vector processing on the corrected circumferential curve to determine a corrected circumferential motion trajectory. Perform filter screening of irregular trajectories within a preset error range for the target circumferential motion trajectory based on the corrected circumferential motion trajectory to obtain an ideal circumferential motion trajectory of the bearing retainer for wind power generation. Generate a corresponding ideal circumferential space region and a corresponding predicted circumferential space region for the ideal circumferential motion trajectory and the predicted circumferential motion trajectory respectively, and perform positioning and comparison of the probability centroids of the space regions for the ideal circumferential space region and the predicted circumferential space region to obtain a predicted overlapping space region. Specifically, Based on the ideal circumferential motion trajectory and the predicted circumferential motion trajectory, generate a first helical cylinder corresponding to the ideal circumferential space region and a second helical cylinder corresponding to the predicted circumferential space region respectively. Both the first helical cylinder and the second helical cylinder include a plurality of point position information. Obtain the first point position information in the first helical cylinder. Based on the significance of the probability distribution function, obtain the point distribution plane region corresponding to the first point position information, and use the probability density function to position the centroid of the helical cylinder for the point distribution plane region to obtain the first centroid position information of the first helical cylinder. Position the centroid of the point distribution plane region related to the second helical cylinder to obtain the second centroid position information of the second helical cylinder. Based on the first centroid position information and the second centroid position information, perform three-dimensional space overlapping comparison of the same time region and the same space region for the first helical cylinder and the second helical cylinder to determine a predicted overlapping space region that overlaps with the first helical cylinder and the second helical cylinder. Based on the predicted overlapping space region, determine whether there is an abnormality in the operating status of the bearing retainer for wind power generation to obtain the operating monitoring information of the wind power bearing. Specifically, Based on the actual circumferential motion trajectory corresponding to the next period, determining the third helical cylinder of the related actual circumferential space region, wherein the actual circumferential motion trajectory is the point circumferential motion trajectory of the next period from the ideal circumferential motion trajectory, Positioning the centroid of the related point distribution plane region with respect to the third helical cylinder to obtain the third centroid position information of the third helical cylinder, Based on the third centroid position information, performing a three-dimensional space overlap comparison of the same time region and the same space region for the first helical cylinder and the third helical cylinder to obtain a true overlap space region, Judging whether there is an abnormality in the operating condition of the bearing retainer for wind power generation based on the size judgment information of the space region of the true overlap space region and the predicted overlap space region, obtaining the operating monitoring information of the wind power generation bearing, and completing the operating monitoring of the wind power generation unit. The method for operating monitoring of a bearing retainer for wind power generation is characterized by including the above.

2. Determining the point tracking information of all sensor chips from the secondary coordinate data and the target coordinate data of the first sensor chip, specifically, Performing weighted fusion of the related coordinate data on the secondary coordinate data in the adjacent cluster head nodes and the main coordinate data in the main cluster head node according to the target period to obtain the target coordinate data of the first sensor chip, Based on the preset grid structure of the WSN, determining the signal transmission node of the first sensor chip as an adjacent cluster head node and determining the target coordinate data as adjacent coordinate data, After performing minimum value processing on the average space distance between the coordinate data of the fourth sensor chip and the target coordinate data of the first sensor chip, obtaining the target coordinate data of the second sensor chip through weighted fusion of the coordinate data, wherein the fourth sensor chip and the first sensor chip are both placed at positions adjacent to the left and right of the second sensor chip, In this way, performing weighted fusion of the related coordinate data for all sensor chips, respectively determining the target coordinate data of all sensor chips, and obtaining the corresponding acceleration data of the plurality of sensor chips during the target period. The method for monitoring the operation of a bearing retainer for wind power generation according to claim 1, characterized by including determining the point tracking information of all sensor chips from the target coordinate data and the corresponding acceleration data of all sensor chips.

3. At least one processor, and a memory communicably connected to the at least one processor, wherein the memory stores instructions executable by the at least one processor, whereby the at least one processor can execute the method for monitoring the operation of a bearing retainer for wind power generation according to claim 1 or 2. An apparatus for monitoring the operation of a bearing retainer for wind power generation, characterized in that.

Images