Analysis method of small probability failure of wind turbine bearing lubrication based on evidence theory

Through the analysis method of low probability failure of wind turbine bearing lubrication based on evidence theory, the problem of failure of wind turbine bearing lubrication system in long-term operation is solved, the reliability and stability of the lubrication system are improved, and more accurate lubrication is achieved control.

CN118865004BActive Publication Date: 2024-11-22HUNAN INSTITUTE OF ENGINEERING
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411365942.X
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-09-29
Publication Date
2024-11-22
Estimated Expiration
2044-09-29

AI Technical Summary

Technical Problem

Wind generator bearing lubrication system is prone to friction and wear during long-term operation, resulting in failure. The existing monitoring methods lack automaticity and accuracy, making it difficult to effectively improve the reliability and stability of bearing lubrication.

Method used

The low probability failure analysis method of wind turbine bearing lubrication based on evidence theory is used to obtain bearing images, running speed and lubricant margin, determine the lubricant coverage position, and conduct low probability failure analysis based on evidence theory to obtain the probability of lubricant failure. , and then control the lubrication system.

Benefits of technology

It improves the accuracy and adaptability of bearing lubrication, enhances the reliability and stability of the lubrication system, and achieves smarter lubrication control.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118865004B_ABST
    Figure CN118865004B_ABST
Patent Text Reader

Abstract

The present disclosure relates to a wind turbine bearing lubrication low probability failure analysis method based on evidence theory, and relates to the field of computer technology; based on evidence theory, a low probability failure analysis method is adopted, which can improve the accuracy of the final low probability failure analysis result, and the accuracy is reflected in the adaptability to the actual bearing lubrication scenario, that is, in the bearing lubrication scenario, lubrication failure is a low probability event, so the analysis result obtained by using the low probability failure analysis is more accurate. Therefore, the technical solution can realize the low probability failure analysis of the wind turbine bearing lubrication based on evidence theory, and then control the wind turbine bearing lubrication system based on the failure analysis result, so as to improve the reliability and stability of the bearing lubrication.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present disclosure relates to the field of computer technology, and in particular to a method for analyzing low-probability failures of wind turbine bearing lubrication based on evidence theory. Background Art

[0002] With the development of renewable energy technology, wind turbines have also developed. Wind turbines can convert the kinetic energy of wind into electrical energy. Wind turbines include wind rotors and generators. The wind rotors are composed of blades, hubs, and reinforcements. Among the hubs and wind rotors, bearing components are involved. The bearing components can realize the transmission of the corresponding components so that the wind turbine can operate stably.

[0003] The bearing lubrication of wind turbines is a key factor in ensuring their long-term stable operation. The lubrication system usually includes main bearing lubrication, yaw bearing lubrication, and pitch bearing lubrication. A good lubrication system can reduce bearing friction, reduce wear, extend service life, and ensure the safe and efficient operation of wind turbines. Summary of the invention

[0004] The purpose of the present disclosure is to provide a wind turbine bearing lubrication small probability failure analysis method based on evidence theory, which can improve the reliability and stability of bearing lubrication.

[0005] In order to achieve the above-mentioned purpose, the present disclosure provides a method for analyzing the low-probability failure of wind turbine bearing lubrication based on evidence theory, including: obtaining a preset bearing image of the wind turbine, the bearing operating speed of the wind turbine and the lubricant residue in the lubrication pump of the wind turbine bearing lubrication system; based on the preset bearing image, determining the lubricant coverage position on the bearing of the wind turbine; based on evidence theory, performing a low-probability failure analysis on the lubricant coverage position, the bearing operating speed and the lubricant residue to obtain a low-probability failure analysis result, and the low-probability failure analysis result is used to characterize the probability of the bearing lubrication failure; based on the low-probability failure analysis result, controlling the wind turbine bearing lubrication system.

[0006] Optionally, the preset bearing image includes a first bearing image corresponding to a lubricated state of the bearing and a second bearing image corresponding to an unlubricated state of the bearing, and determining the lubricant coverage position on the bearing of the wind turbine based on the preset bearing image includes: performing image feature extraction based on the first bearing image to obtain a first image feature, wherein the first image feature is associated with the bearing and the lubricant; determining a first lubricant coverage position based on the first image feature; performing image feature extraction based on the second bearing image to obtain a second image feature, wherein the bearing position associated with the second image feature is different from the bearing position associated with the first image feature; obtaining a bearing lubrication strategy of the wind turbine bearing lubrication system; determining a second lubricant coverage position based on the bearing lubrication strategy and the second image feature; and determining a final lubricant coverage position based on the first lubricant coverage position and the second lubricant coverage position.

[0007] Optionally, the bearing lubrication strategy includes the flow direction and flow speed of the lubricant in the bearing, and determining the second lubricant coverage position based on the bearing lubrication strategy and the second image feature includes: sorting the second image features based on the running direction of the bearing to obtain sorted second image features; determining the traversal strategy corresponding to the sorted second image features based on the flow direction and the flow speed, the traversal strategy including the traversal direction and the number of traversal interval features; traversing and sampling the sorted second image features based on the traversal strategy to obtain traversal results; and determining the second lubricant coverage position based on the traversal results.

[0008] Optionally, based on the evidence theory, a small probability failure analysis is performed on the lubricant coverage position, the bearing operating speed and the lubricant residue to obtain a small probability failure analysis result, including: determining a first lubrication failure probability based on the evidence theory and the bearing operating speed; determining a second lubrication failure probability based on the evidence theory, the bearing operating speed and the lubricant residue; determining a small probability failure analysis result based on the first lubrication failure probability, the second lubrication failure probability and the lubricant coverage position.

[0009] Optionally, the wind turbine bearing lubrication low-probability failure analysis method based on evidence theory also includes: obtaining a preset reliability analysis model based on evidence theory, the reliability analysis model includes a first evidence body and a second evidence body, the evidence theory corresponding to the first evidence body is the corresponding relationship between the bearing operating speed variable and the lubrication failure probability, and the evidence theory corresponding to the second evidence body is the corresponding relationship between the coupling variable of the bearing operating speed and the lubricant residue and the lubrication failure probability; correspondingly, determining the first lubrication failure probability based on the evidence theory and the bearing operating speed includes: determining the first lubrication failure probability based on the bearing operating speed and the first evidence body through the preset reliability analysis model based on evidence theory; correspondingly, determining the second lubrication failure probability based on the evidence theory, the bearing operating speed and the lubricant residue includes: determining the coupling variable based on the bearing operating speed and the lubricant residue; determining the second lubrication failure probability based on the coupling variable and the first evidence body through the preset reliability analysis model based on evidence theory.

[0010] Optionally, the preset reliability analysis model based on evidence theory also includes a variable coupling module, and the coupling principle of the variable coupling module is determined based on the failure domain division result of the first evidence body for the variable; correspondingly, determining the coupling variable based on the bearing operating speed and the lubricant residue includes: obtaining the failure domain division result of the first evidence body for the bearing operating speed through the variable coupling module; determining the coupling principle based on the failure domain division result of the first evidence body for the bearing operating speed; coupling the bearing operating speed and the lubricant residue based on the coupling principle through the variable coupling module to determine the coupling variable.

[0011] Optionally, determining a small probability failure analysis result based on the first lubrication failure probability, the second lubrication failure probability and the lubrication coverage position includes: if the first lubrication failure probability and the second lubrication failure probability are not equal, determining a small probability failure analysis result based on the minimum lubrication failure probability of the first lubrication failure probability and the second lubrication failure probability; if the first lubrication failure probability and the second lubrication failure probability are equal, determining a third lubrication failure probability based on evidence theory, the lubricant residue and the lubrication coverage position; determining a small probability failure analysis result based on any lubrication failure probability of the first lubrication failure probability and the second lubrication failure probability and the third lubrication failure probability.

[0012] Optionally, the small probability failure analysis result includes the lubrication failure probability and the failure analysis variables involved in the small probability failure analysis, and the controlling of the wind turbine bearing lubrication system based on the small probability failure analysis result includes: if the number of the failure analysis variables is less than or equal to the preset number of variables, and the lubrication failure probability is greater than the preset probability, determining the lubrication adjustment parameters of the wind turbine bearing lubrication system based on the failure analysis variables; if the number of the failure analysis variables is greater than the preset number of variables, and the lubrication failure probability is less than the preset probability, determining the lubrication adjustment parameters of the wind turbine bearing lubrication system based on any variable in the failure analysis variables; and controlling the wind turbine bearing lubrication system based on the lubrication adjustment parameters of the wind turbine bearing lubrication system.

[0013] Optionally, the preset bearing image includes a first bearing image corresponding to a bearing lubrication state and a second bearing image corresponding to an unlubricated bearing state. Based on the preset bearing image, the wind turbine bearing lubrication small probability failure analysis method based on evidence theory also includes: obtaining a third bearing image after controlling the wind turbine bearing lubrication system; determining the probability of bearing lubrication control failure based on the first bearing image, the second bearing image and the third bearing image; and performing secondary control on the wind turbine bearing lubrication system based on the probability of bearing lubrication control failure.

[0014] Optionally, determining the probability of bearing lubrication control failure based on the first bearing image, the second bearing image and the third bearing image includes: performing image feature extraction based on the first bearing image to obtain a first image feature; performing image feature extraction based on the second bearing image to obtain a second image feature; performing image feature extraction based on the third bearing image to obtain a third image feature; determining a first similarity between the third image feature and the first image feature, and determining a second similarity between the third image feature and the second image feature; determining the probability of bearing lubrication control failure based on the maximum similarity, the minimum similarity in the first similarities and the maximum similarity in the second similarities.

[0015] Through the above technical solution, the preset bearing image of the wind turbine, the bearing running speed of the wind turbine and the lubricant residue in the lubrication pump of the wind turbine bearing lubrication system are obtained, and the lubricant coverage position is determined based on the preset bearing image; then, the lubricant coverage position, the bearing running speed and the lubricant residue are used as analysis variables, and the analysis is performed based on the evidence theory to obtain the small probability failure analysis result that characterizes the probability of bearing lubrication failure. Based on the small probability failure analysis result, the wind turbine bearing lubrication system can be controlled. Since the small probability failure analysis method is adopted based on the evidence theory, the accuracy of the small probability failure analysis result finally obtained can be improved. The accuracy is reflected in the adaptability to the actual bearing lubrication scenario, that is, in the bearing lubrication scenario, lubrication failure is a small probability event, so the analysis result obtained by using the small probability failure analysis is more accurate. Therefore, the technical solution can realize the small probability failure analysis of the wind turbine bearing lubrication based on the evidence theory, and then control the wind turbine bearing lubrication system based on the failure analysis result, so as to improve the reliability and stability of the bearing lubrication.

[0016] Other features and advantages of the present disclosure will be described in detail in the following detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The accompanying drawings are used to provide a further understanding of the present disclosure and constitute a part of the specification. Together with the following specific embodiments, they are used to explain the present disclosure but do not constitute a limitation of the present disclosure. In the accompanying drawings:

[0018] Figure 1 It is a structural block diagram of an intelligent bearing lubrication system according to an exemplary embodiment.

[0019] Figure 2 It is a flow chart of a method for analyzing low-probability failure of wind turbine bearing lubrication based on evidence theory according to an exemplary embodiment.

[0020] Figure 3 It is a structural block diagram of a reliability analysis model based on evidence theory according to an exemplary embodiment.

[0021] Figure 4 is a structural block diagram of another reliability analysis model according to an exemplary embodiment

[0022] Figure 5 It is a block diagram of a wind turbine bearing lubrication low-probability failure analysis device based on evidence theory according to an exemplary embodiment.

[0023] Figure 6 It is a block diagram of an electronic device according to an exemplary embodiment. DETAILED DESCRIPTION

[0024] The specific implementation of the present disclosure is described in detail below in conjunction with the accompanying drawings. It should be understood that the specific implementation described herein is only used to illustrate and explain the present disclosure, and is not used to limit the present disclosure.

[0025] In various application scenarios of wind turbines, bearing lubrication of wind turbines is a key factor in ensuring their long-term stable operation. The lubrication system usually includes main bearing lubrication, yaw bearing lubrication, and pitch bearing lubrication. A good lubrication system can reduce bearing friction, reduce wear, extend service life, and ensure the safe and efficient operation of wind turbines.

[0026] Therefore, in these application scenarios, the bearing lubrication effect of the wind turbine can be analyzed to achieve more intelligent bearing lubrication control based on the analysis results.

[0027] Figure 1 is a structural block diagram of an intelligent bearing lubrication system according to an exemplary embodiment. Figure 1 As shown, the lubrication system mainly includes a lubrication oil pump, an oil filter, a lubrication pipeline, a metering device and a monitoring device.

[0028] Among them, the lubricating oil pump, oil filter, lubricating pipeline and metering device are the basic components of the lubrication system, which can realize the delivery of lubricant to the wind turbine bearing. For the specific implementation of these components, reference can be made to the mature technology in the field.

[0029] Regarding the monitoring device, the bearing lubrication can be monitored to control the entire lubrication system more intelligently based on the monitoring results.

[0030] Therefore, the technical solution provided by the embodiments of the present disclosure can be applied to monitoring devices.

[0031] In the related art, in order to achieve accurate monitoring of bearing lubrication, monitoring personnel are usually deployed to regularly check the monitoring images of the bearings and adjust the control scheme of the bearing lubrication according to the monitoring images. This monitoring method is not automatic and has low accuracy.

[0032] Based on this, the embodiment of the present disclosure provides a technical solution, which is based on evidence theory and adopts a small probability failure analysis method, which can improve the accuracy of the final small probability failure analysis results. The accuracy is reflected in the adaptability to the actual bearing lubrication scenario, that is, in the bearing lubrication scenario, lubrication failure is a small probability event, so using small probability failure analysis, the analysis results obtained are more accurate.

[0033] Figure 2is a flow chart of a method for analyzing a small probability failure of a wind turbine bearing lubrication based on evidence theory according to an exemplary embodiment. Figure 2 As shown, the method includes:

[0034] Step S21, obtaining a preset bearing image of the wind turbine generator, a bearing running speed of the wind turbine generator, and a lubricant remaining in a lubrication pump of a bearing lubrication system of the wind turbine generator.

[0035] Step S22: determining the lubricant coverage position on the bearing of the wind turbine based on the preset bearing image.

[0036] Step S23, based on the evidence theory, a small probability failure analysis is performed on the lubricant coverage position, the bearing running speed and the lubricant residue to obtain a small probability failure analysis result, which is used to characterize the probability of bearing lubrication failure.

[0037] Step S24: controlling the wind turbine bearing lubrication system based on the low probability failure analysis result.

[0038] In step S21, the preset bearing image may be a bearing image collected during the normal operation of the bearing, which may include a first bearing image corresponding to a lubricated state of the bearing and a second bearing image corresponding to an unlubricated state of the bearing.

[0039] Regarding the lubrication state of the bearing, it can be understood as the state just after lubrication by the lubrication system. Regarding the unlubricated state of the bearing, it can be understood as the state without lubrication for a long time, for example: the time since the last lubrication by the lubrication system is long.

[0040] The bearing running speed of the wind turbine generator can be the real-time data of the wind turbine generator, and the real-time data can be data at one or more time points. The bearing running speed can be: the transmission speed, which can be measured by the corresponding speed measuring device of the bearing.

[0041] The lubricant residue in the lubrication pump of the wind turbine bearing lubrication system can be obtained by a corresponding residue monitoring device of the lubrication pump.

[0042] Regarding the bearing running speed and lubricant surplus, it can be understood as real-time data within a period of time, that is, it includes not only a running speed value, or not only a surplus value.

[0043] In step S22, based on the preset bearing image, the lubricant covering position is first determined. The lubricant covering position can be understood as the bearing position involved in the lubrication control.

[0044] It can be understood that when lubricating the bearing, it is not necessary to lubricate all bearing positions. Only some positions need to be lubricated to achieve the effects of reducing friction and wear of the bearing. Therefore, the lubricant coverage position can be determined.

[0045] As an optional implementation, step S22 includes: performing image feature extraction based on the first bearing image to obtain a first image feature, the first image feature being associated with the bearing and the lubricant; determining a first lubricant coverage position based on the first image feature; performing image feature extraction based on the second bearing image to obtain a second image feature, the bearing position associated with the second image feature being different from the bearing position associated with the first image feature; obtaining a bearing lubrication strategy for a wind turbine bearing lubrication system; determining a second lubricant coverage position based on the bearing lubrication strategy and the second image feature; and determining a final lubricant coverage position based on the first lubricant coverage position and the second lubricant coverage position.

[0046] In this embodiment, the bearing lubrication position is determined by image processing. It can be understood that the bearing image can reflect the characteristics of the bearing, and its image position can also correspond to the actual bearing position.

[0047] In some embodiments, the first image feature may be a pixel feature related to two objects, the bearing and the lubricant.

[0048] In some embodiments, the image recognition model may be used to first identify the bearing area and then the lubricant area. The implementation of the image recognition model may refer to mature object recognition technology in the art, which will not be described in detail here.

[0049] Based on the identified bearing area and lubricant area, the overlapping area is determined, and then the overlapping area is divided into multiple sub-areas. The pixel features of these multiple sub-areas can be regarded as the first image feature, so that the first image feature is associated with both the bearing and the lubricant.

[0050] Further, based on the first image feature, the first lubricant coverage position can be determined. For example, on the basis that the first image feature is a pixel feature, the position of the pixel corresponding to the pixel feature in the image is corresponded to the actual bearing position to determine the first lubricant coverage position, for example: the position of one-third of the circumference of the bearing. It should be noted that the first lubricant coverage position is at least one non-repeating bearing position.

[0051] In some embodiments, the implementation method of extracting image features based on the second bearing image to obtain the second image features can refer to the extraction method of the first image features. The difference is that the lubricant does not need to be considered here, that is, when performing object recognition, the lubricant can be ignored as an identified object.

[0052] In some embodiments, the bearing position associated with the second image feature is different from the bearing position associated with the first image feature, that is, the pixels corresponding to the second image feature do not overlap with the pixels corresponding to the first image feature. According to this limitation, the required second image feature can be extracted.

[0053] Furthermore, the bearing lubrication strategy of the wind turbine bearing lubrication system may be a pre-established strategy, which determines the lubrication method of the bearing. Based on the strategy and the second image feature, the second lubricant coverage position is determined, and then the two coverage positions are combined to determine the final coverage position.

[0054] In some embodiments, the bearing lubrication strategy includes the flow direction and flow speed of the lubricant in the bearing, wherein the flow direction may be a fixed flow direction, and the flow speed may be a real flow speed calculated based on multiple lubrication data, or a predicted flow speed.

[0055] In some embodiments, based on the bearing lubrication strategy and the second image features, determining the second lubricant coverage position includes: sorting the second image features based on the running direction of the bearing to obtain sorted second image features; determining the traversal strategy corresponding to the sorted second image features based on the flow direction and flow speed, the traversal strategy including the traversal direction and the number of traversal interval features; traversing and sampling the sorted second image features based on the traversal strategy to obtain traversal results; and determining the second lubricant coverage position based on the traversal results.

[0056] In some embodiments, the running direction of the bearing may be a fixed running direction, for example, a clockwise direction. Based on the clockwise direction and the real bearing position corresponding to the second image feature, the second image features may be sorted, for example, the image features corresponding to the position close to the starting running point in the clockwise direction are sorted first.

[0057] In some embodiments, if the flow direction is consistent with the running direction of the bearing, the traversal direction is traversal according to the sorting; if the flow direction is inconsistent with the running direction of the bearing, the traversal direction can be traversal in reverse order of the sorting.

[0058] In some embodiments, the faster the flow speed, the smaller the number of traversed interval features; the slower the flow speed, the larger the number of traversed interval features. It can be understood that if the flow speed is fast, more positions can be covered as much as possible, so when traversing, it is necessary to traverse as many features as possible.

[0059] Further, based on the traversal strategy, the sorted second image features are traversed and sampled to obtain traversal sampling results, which include multiple bearing positions, based on which the second lubricant covering position can be determined. For example, the multiple bearing positions are directly determined as the second lubricant covering position.

[0060] Furthermore, deduplication processing is performed based on the first lubricant covering position and the second lubricant covering position to obtain a final lubricant covering position. It can be understood that the number of the covering positions is multiple.

[0061] In step S23, based on the evidence theory, a small probability failure analysis is performed on the lubricant coverage position, the bearing running speed and the lubricant residue.

[0062] Regarding evidence theory, variables can be divided into failure domains based on reliability analysis. Variables can be variables defined based on evidence bodies. Thus, evidence theory can be used for small probability failure analysis.

[0063] As an optional implementation, step S23 includes: determining the first lubrication failure probability based on evidence theory and bearing operating speed; determining the second lubrication failure probability based on evidence theory, bearing operating speed and lubricant residue; determining the small probability failure analysis result based on the first lubrication failure probability, the second lubrication failure probability and the lubricant coverage position.

[0064] In this embodiment, the bearing operating speed can be determined as a variable to determine the first lubrication failure probability; then, the bearing operating speed and the lubricant residue can be determined as another variable to determine the second lubrication failure probability; further, the two failure probabilities and the lubricant coverage position are integrated to determine the small probability failure analysis result.

[0065] In some embodiments, the lubrication failure probability may be determined by a reliability analysis model based on evidence theory.

[0066] Figure 3 is a structural block diagram of a reliability analysis model based on evidence theory according to an exemplary embodiment. Figure 3 As shown, the reliability analysis model includes a first evidence body and a second evidence body.

[0067] Among them, the evidence theory corresponding to the first evidence body is the corresponding relationship between the bearing running speed variable and the lubrication failure probability, and the evidence theory corresponding to the second evidence body is the corresponding relationship between the coupling variable of the bearing running speed and the lubricant residue and the lubrication failure probability.

[0068] In some embodiments, the above correspondence can be expressed as an evidence theory formula. For example, the correspondence between the bearing speed variable and the probability of lubrication failure can be expressed as f(x1), and the correspondence between the coupling variable of the bearing speed and the lubricant residue and the probability of lubrication failure can be expressed as f(x2). The specific forms of f(x1) and f(x2) can be determined by actual measurements according to different application scenarios. For example, the bearing speed variable is inversely proportional to the probability of lubrication failure, and the coupling variable of the bearing speed and the lubricant residue is in direct proportion to the probability of lubrication failure.

[0069] Correspondingly, based on the evidence theory and the bearing running speed, the first lubrication failure probability is determined, including: determining the first lubrication failure probability based on the bearing running speed and the first evidence body through a preset reliability analysis model based on the evidence theory; Correspondingly, based on the evidence theory, the second lubrication failure probability is determined, including: determining the coupling variables based on the bearing running speed and the lubricant residue; determining the second lubrication failure probability based on the coupling variables and the first evidence body through a preset reliability analysis model based on the evidence theory.

[0070] It can be understood that, based on the evidence body constructed by the model, the evidence body can be divided into failure domains based on corresponding variables and corresponding evidence theories, thereby determining the lubrication failure probability. For example, the lubrication failure probability is the ratio of the number of variable values ​​divided into the failure domain among multiple variable values ​​to the total number of multiple variable values.

[0071] Figure 4 is a structural block diagram of another reliability analysis model according to an exemplary embodiment. Figure 4 As shown, the reliability analysis model also includes a variable coupling module, and the coupling principle of the variable coupling module is determined based on the failure domain division result of the first evidence body for the variable.

[0072] Correspondingly, based on the bearing operating speed and the lubricant residue, the coupling variable is determined, including: obtaining the failure domain division result of the first evidence body for the bearing operating speed through the variable coupling module; determining the coupling principle based on the failure domain division result of the first evidence body for the bearing operating speed; coupling the bearing operating speed and the lubricant residue based on the coupling principle through the variable coupling module to determine the coupling variable.

[0073] In some embodiments, if the number of variables in the failure domain exceeds the preset number of variables in the failure domain division result of the first body of evidence for the bearing running speed, the weight of the bearing running speed is less than the weight of the lubricant residue in the coupling principle. Otherwise, the weight of the bearing running speed is greater than the weight of the lubricant residue.

[0074] Based on the weights corresponding to the variables, the two variables can be coupled to obtain coupled variables.

[0075] In some embodiments, a small probability failure analysis result is determined based on a first lubrication failure probability, a second lubrication failure probability and a lubrication coverage position, including: if the first lubrication failure probability and the second lubrication failure probability are not equal, determining the small probability failure analysis result based on the minimum lubrication failure probability of the first lubrication failure probability and the second lubrication failure probability; if the first lubrication failure probability and the second lubrication failure probability are equal, determining the third lubrication failure probability based on evidence theory, lubricant residue and lubrication coverage position; determining the small probability failure analysis result based on any lubrication failure probability of the first lubrication failure probability and the second lubrication failure probability and the third lubrication failure probability.

[0076] In this embodiment, if the first lubrication failure probability and the second lubrication failure probability are not equal, the lubrication failure probability of the lubrication coverage position may be the minimum lubrication failure probability.

[0077] If the first lubrication failure probability and the second lubrication failure probability are equal, the third lubrication failure probability can also be determined by using the evidence theory, lubricant residue and lubricant coverage position. Accordingly, the second evidence body can be continued to be used, but the lubricant coverage position and lubricant residue are coupled to obtain a new coupling variable.

[0078] Among them, when the lubrication coverage position and the lubricant residue are coupled, the weight of the lubrication coverage position is greater than the weight of the lubricant residue, and the weight of the lubrication coverage position is determined based on the distance from the starting running position of the bearing. The larger the distance, the greater the weight.

[0079] Furthermore, the third lubrication failure probability is determined in the same manner, and then any one of the first lubrication failure probability and the second lubrication failure probability is taken, combined with the third lubrication failure probability, and according to the aforementioned implementation method, a small probability failure analysis result is determined.

[0080] In some embodiments, failure analysis variables involved in the failure analysis are determined, and based on the failure analysis variables and the lubrication failure probability, a low-probability failure analysis result is determined.

[0081] Furthermore, the small probability failure analysis result includes the lubrication failure probability and failure analysis variables involved in the small probability failure analysis, the failure analysis variables, for example, at least two of the bearing running speed, lubricant remaining amount and lubrication coverage position.

[0082] In step S24, based on the low probability failure analysis result, the wind turbine bearing lubrication system is controlled.

[0083] In some embodiments, step S24 may include: if the number of failure analysis variables is less than or equal to the preset number of variables, and the probability of lubrication failure is greater than the preset probability, determining the lubrication adjustment parameters of the wind turbine bearing lubrication system based on the failure analysis variables; if the number of failure analysis variables is greater than the preset number of variables, and the probability of lubrication failure is less than the preset probability, determining the lubrication adjustment parameters of the wind turbine bearing lubrication system based on any variable in the failure analysis variables; and controlling the wind turbine bearing lubrication system based on the lubrication adjustment parameters of the wind turbine bearing lubrication system.

[0084] In some embodiments, the preset number of variables is 2 and the preset probability is 50%.

[0085] Further, determining the lubrication adjustment parameters of the wind turbine bearing lubrication system based on the failure analysis variables may include: determining a separate lubrication adjustment parameter based on each failure analysis variable. For example, determining a flow velocity adjustment value and a lubricant usage value based on the lubricant remaining amount, and determining a flow direction adjustment value based on the bearing running speed.

[0086] The lubrication adjustment parameter of the wind turbine bearing lubrication system is determined based on any one of the failure analysis variables. It can be understood that a variable is selected to determine the lubrication adjustment parameter without considering all the failure analysis variables.

[0087] In some embodiments, controlling the wind turbine bearing lubrication system based on the lubrication adjustment parameters of the wind turbine bearing lubrication system can be understood as generating control instructions to the corresponding execution unit and sending them to the execution unit so that the execution unit executes the corresponding control command.

[0088] In some embodiments, after performing bearing lubrication control, the method may also include: obtaining a third bearing image after controlling the wind turbine bearing lubrication system; determining the probability of bearing lubrication control failure based on the first bearing image, the second bearing image and the third bearing image; and performing secondary control on the wind turbine bearing lubrication system based on the probability of bearing lubrication control failure.

[0089] In some embodiments, the probability of bearing lubrication control failure is determined based on the first bearing image, the second bearing image and the third bearing image, including: performing image feature extraction based on the first bearing image to obtain a first image feature; performing image feature extraction based on the second bearing image to obtain a second image feature; performing image feature extraction based on the third bearing image to obtain a third image feature; determining a first similarity between the third image feature and the first image feature, and determining a second similarity between the third image feature and the second image feature; determining the probability of bearing lubrication control failure based on the maximum similarity in the first similarity, the minimum similarity in the second similarity and the maximum similarity in the second similarity.

[0090] In some embodiments, image feature extraction is performed based on the first bearing image to obtain the first image feature, and image feature extraction is performed based on the second bearing image to obtain the second image feature. The description of the aforementioned embodiments can be referred to and will not be repeated here.

[0091] Furthermore, image feature extraction is performed based on the third bearing image to obtain a third image feature. The method for extracting the first image feature and the second image feature may also be referred to. Specifically, the method for extracting the first image feature may be referred to.

[0092] In some embodiments, the method for calculating the similarity of image features can refer to mature image processing technology in the art and will not be introduced in detail here.

[0093] It can be understood that there may be multiple first image features, multiple second image features, and multiple third image features, so there may also be multiple first similarities and multiple second similarities.

[0094] Therefore, the probability of bearing lubrication control failure may be determined based on the maximum similarity among the first similarities, the minimum similarity among the first similarities, and the maximum similarity among the second similarities.

[0095] In some embodiments, if the maximum similarity and the minimum similarity in the first similarity are both greater than the maximum similarity in the second similarity, the probability of bearing lubrication control failure may be low, for example, in the range of 0% to 10%. If any of the maximum similarity and the minimum similarity in the first similarity is less than the maximum similarity in the second similarity, the probability of bearing lubrication control failure may be high, for example, in the range of 90% to 100%.

[0096] Furthermore, based on the probability of bearing lubrication control failure, secondary control of the wind turbine bearing lubrication system may include, if the probability of bearing lubrication control failure is low, lubricating the bearing again after a normal lubrication cycle. If the probability of bearing lubrication control failure is high, lubricating the bearing again after a short interval (e.g., 1 / 3 of the normal lubrication cycle). That is, the secondary control mainly controls the time of the next bearing lubrication.

[0097] Through the above technical solution, the preset bearing image of the wind turbine, the bearing running speed of the wind turbine and the lubricant residue in the lubrication pump of the wind turbine bearing lubrication system are obtained, and the lubricant coverage position is determined based on the preset bearing image; then, the lubricant coverage position, the bearing running speed and the lubricant residue are used as analysis variables, and the analysis is performed based on the evidence theory to obtain the small probability failure analysis result that characterizes the probability of bearing lubrication failure. Based on the small probability failure analysis result, the wind turbine bearing lubrication system can be controlled. Since the small probability failure analysis method is adopted based on the evidence theory, the accuracy of the small probability failure analysis result finally obtained can be improved. The accuracy is reflected in the adaptability to the actual bearing lubrication scenario, that is, in the bearing lubrication scenario, lubrication failure is a small probability event, so the analysis result obtained by using the small probability failure analysis is more accurate. Therefore, the technical solution can realize the small probability failure analysis of the wind turbine bearing lubrication based on the evidence theory, and then control the wind turbine bearing lubrication system based on the failure analysis result, so as to improve the reliability and stability of the bearing lubrication.

[0098] Figure 5 is a block diagram of a wind turbine bearing lubrication low probability failure analysis device based on evidence theory according to an exemplary embodiment. Figure 5 As shown, the device comprises:

[0099] An acquisition module 501 is used to acquire a preset bearing image of a wind turbine, a bearing running speed of the wind turbine, and a lubricant remaining in a lubrication pump of a bearing lubrication system of the wind turbine;

[0100] The analysis module 502 is used to determine the lubricant coverage position on the bearing of the wind turbine based on the preset bearing image; based on the evidence theory, perform a small probability failure analysis on the lubricant coverage position, the bearing operating speed and the lubricant residue to obtain a small probability failure analysis result, and the small probability failure analysis result is used to characterize the probability of the bearing lubrication failure; based on the small probability failure analysis result, control the wind turbine bearing lubrication system.

[0101] Regarding the device in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0102] Figure 6 FIG. 6 is a block diagram of an electronic device 600 according to an exemplary embodiment. Figure 6 As shown, the electronic device 600 may include: a processor 601 , a memory 602 . The electronic device 600 may also include one or more of a multimedia component 603 , an input / output (I / O) interface 604 , and a communication component 605 .

[0103] The processor 601 is used to control the overall operation of the electronic device 600 to complete all or part of the steps in the above-mentioned wind turbine bearing lubrication low probability failure analysis method based on evidence theory. The memory 602 is used to store various types of data to support the operation of the electronic device 600, and these data may include, for example, instructions for any application or method used to operate on the electronic device 600, and application-related data, such as contact data, sent and received messages, pictures, audio, video, etc. The memory 602 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (Static Random Access Memory, referred to as SRAM), electrically erasable programmable read-only memory (Electrically Erasable Programmable Read-Only Memory, referred to as EEPROM), erasable programmable read-only memory (Erasable Programmable Read-Only Memory, referred to as EPROM), programmable read-only memory (Programmable Read-Only Memory, referred to as PROM), read-only memory (Read-Only Memory, referred to as ROM), magnetic memory, flash memory, magnetic disk or optical disk. The multimedia component 603 may include a screen and an audio component. The screen may be, for example, a touch screen, and the audio component is used to output and / or input audio signals. For example, the audio component may include a microphone, which is used to receive external audio signals. The received audio signal may be further stored in the memory 602 or sent through the communication component 605. The audio component also includes at least one speaker for outputting audio signals. The I / O interface 604 provides an interface between the processor 601 and other interface modules, and the above-mentioned other interface modules may be a keyboard, a mouse, buttons, etc. These buttons may be virtual buttons or physical buttons. The communication component 605 is used for wired or wireless communication between the electronic device 600 and other devices. Wireless communication, such as Wi-Fi, Bluetooth, Near Field Communication (NFC), 2G, 3G or 4G, or a combination of one or more of them, so the corresponding communication component 605 may include: Wi-Fi module, Bluetooth module, NFC module.

[0104] In an exemplary embodiment, the electronic device 600 can be implemented by one or more application specific integrated circuits (ASIC), digital signal processors (DSP), digital signal processing devices (DSPD), programmable logic devices (PLD), field programmable gate arrays (FPGA), controllers, microcontrollers, microprocessors or other electronic components to execute the above-mentioned wind turbine bearing lubrication low-probability failure analysis method based on evidence theory.

[0105] In another exemplary embodiment, a computer-readable storage medium including program instructions is also provided, and when the program instructions are executed by a processor, the steps of the above-mentioned wind turbine bearing lubrication low probability failure analysis method based on evidence theory are implemented. For example, the computer-readable storage medium can be the above-mentioned memory 602 including program instructions, and the above-mentioned program instructions can be executed by the processor 601 of the electronic device 600 to complete the above-mentioned wind turbine bearing lubrication low probability failure analysis method based on evidence theory.

[0106] In another exemplary embodiment, a computer program product is also provided, which includes a computer program executable by a processor, and when the computer program is executed by the processor, the steps of the above-mentioned method for analyzing the low-probability failure of wind turbine bearing lubrication based on evidence theory are implemented.

[0107] The preferred embodiments of the present disclosure are described in detail above in conjunction with the accompanying drawings; however, the present disclosure is not limited to the specific details in the above embodiments. Within the technical concept of the present disclosure, a variety of simple modifications can be made to the technical solution of the present disclosure, and these simple modifications all fall within the protection scope of the present disclosure.

[0108] It should also be noted that the various specific technical features described in the above specific embodiments can be combined in any suitable manner without contradiction. In order to avoid unnecessary repetition, the present disclosure will not further describe various possible combinations.

[0109] In addition, various embodiments of the present disclosure may be arbitrarily combined, and as long as they do not violate the concept of the present disclosure, they should also be regarded as the contents disclosed by the present disclosure.

Claims

1. A wind turbine bearing lubrication small probability failure analysis method based on evidence theory, characterized in that: include: Acquire a preset bearing image of the wind turbine, a bearing running speed of the wind turbine, and a lubricant remaining in a lubrication pump of a bearing lubrication system of the wind turbine; Based on the preset bearing image, determining a lubricant coverage position on a bearing of the wind turbine; Based on the theory of evidence, a small probability failure analysis is performed on the lubricant coverage position, the bearing running speed and the lubricant surplus to obtain a small probability failure analysis result, and the small probability failure analysis result is used to characterize the probability of the bearing lubrication failure; Based on the low-probability failure analysis results, the wind turbine bearing lubrication system is controlled; Based on the evidence theory, a small probability failure analysis is performed on the lubricant coverage position, the bearing running speed and the lubricant residue to obtain a small probability failure analysis result, including: Determining a first lubrication failure probability based on the evidence theory and the bearing operating speed; Determining a second lubrication failure probability based on evidence theory, the bearing operating speed, and the lubricant residue; Determining a low probability failure analysis result based on the first lubrication failure probability, the second lubrication failure probability, and the lubricant coverage position; The wind turbine bearing lubrication low probability failure analysis method based on evidence theory also includes: Obtaining a preset reliability analysis model based on evidence theory, the reliability analysis model includes a first evidence body and a second evidence body, the evidence theory corresponding to the first evidence body is the corresponding relationship between the bearing running speed variable and the lubrication failure probability, and the evidence theory corresponding to the second evidence body is the corresponding relationship between the coupling variable of the bearing running speed and the lubricant residue and the lubrication failure probability; Correspondingly, determining the first lubrication failure probability based on the evidence theory and the bearing running speed includes: Determining a first lubrication failure probability based on the bearing running speed and the first body of evidence by using the preset reliability analysis model based on evidence theory; Correspondingly, based on the evidence theory, the bearing running speed and the lubricant residue, determining the second lubrication failure probability includes: determining a coupling variable based on the bearing operating speed and the lubricant surplus; Determining a second lubrication failure probability based on the coupling variable and the first body of evidence by using the preset reliability analysis model based on evidence theory; The preset reliability analysis model based on evidence theory also includes a variable coupling module, and the coupling principle of the variable coupling module is determined based on the failure domain division result of the first evidence body for the variable; correspondingly, the coupling variable is determined based on the bearing running speed and the lubricant residue, including: Acquire, by means of the variable coupling module, a failure domain division result of the first body of evidence for the running speed of the bearing; Determining a coupling principle based on the failure domain division result of the first body of evidence for the running speed of the bearing; The bearing running speed and the lubricant surplus are coupled based on the coupling principle by the variable coupling module to determine a coupling variable.

2. The method for analyzing low-probability failure of wind turbine bearing lubrication based on evidence theory according to claim 1 is characterized in that: The preset bearing image includes a first bearing image corresponding to a lubricated state of the bearing and a second bearing image corresponding to an unlubricated state of the bearing. The determining of the lubricant coverage position on the bearing of the wind turbine based on the preset bearing image includes: Performing image feature extraction based on the first bearing image to obtain a first image feature, wherein the first image feature is associated with the bearing and the lubricant; determining a first lubricant coverage position based on the first image feature; performing image feature extraction based on the second bearing image to obtain a second image feature, wherein a bearing position associated with the second image feature is different from a bearing position associated with the first image feature; Obtaining a bearing lubrication strategy for the wind turbine bearing lubrication system; determining a second lubricant coverage position based on the bearing lubrication strategy and the second image feature; A final lubricant coverage position is determined based on the first lubricant coverage position and the second lubricant coverage position.

3. The method for analyzing low-probability failure of wind turbine bearing lubrication based on evidence theory according to claim 2 is characterized in that: The bearing lubrication strategy includes a flow direction and a flow speed of the lubricant in the bearing, and determining a second lubricant coverage position based on the bearing lubrication strategy and the second image feature includes: sorting the second image features based on the running direction of the bearing to obtain sorted second image features; Based on the flow direction and the flow speed, determining a traversal strategy corresponding to the sorted second image features, the traversal strategy including a traversal direction and a number of traversal interval features; Performing traversal sampling on the sorted second image features based on the traversal strategy to obtain a traversal result; Based on the traversal result, the second lubricant coverage position is determined.

4. The method for analyzing low-probability failure of wind turbine bearing lubrication based on evidence theory according to claim 1 is characterized in that: The determining of a small probability failure analysis result based on the first lubrication failure probability, the second lubrication failure probability and the lubrication coverage position includes: If the first lubrication failure probability and the second lubrication failure probability are not equal, determining a small probability failure analysis result based on a minimum lubrication failure probability between the first lubrication failure probability and the second lubrication failure probability; If the first lubrication failure probability is equal to the second lubrication failure probability, determining a third lubrication failure probability based on evidence theory, the lubricant residue and the lubrication coverage position; Based on any one of the first lubrication failure probability and the second lubrication failure probability and the third lubrication failure probability, a low probability failure analysis result is determined.

5. The method for analyzing low-probability failure of wind turbine bearing lubrication based on evidence theory according to claim 1 is characterized in that: The small probability failure analysis result includes the lubrication failure probability and the failure analysis variables involved in the small probability failure analysis. The controlling of the wind turbine bearing lubrication system based on the small probability failure analysis result includes: If the number of the failure analysis variables is less than or equal to the preset number of variables, and the lubrication failure probability is greater than the preset probability, determining the lubrication adjustment parameters of the wind turbine bearing lubrication system based on the failure analysis variables; If the number of the failure analysis variables is greater than the preset number of variables, and the lubrication failure probability is less than the preset probability, determining the lubrication adjustment parameter of the wind turbine bearing lubrication system based on any variable in the failure analysis variables; Based on the lubrication adjustment parameters of the wind turbine generator bearing lubrication system, the wind turbine generator bearing lubrication system is controlled.

6. The method for analyzing low-probability failure of wind turbine bearing lubrication based on evidence theory according to claim 1 is characterized in that: The preset bearing image includes a first bearing image corresponding to a bearing lubrication state and a second bearing image corresponding to a bearing unlubricated state. Based on the preset bearing image, the wind turbine bearing lubrication small probability failure analysis method based on evidence theory also includes: Acquiring a third bearing image after controlling the wind turbine bearing lubrication system; determining a probability of bearing lubrication control failure based on the first bearing image, the second bearing image, and the third bearing image; Based on the probability of bearing lubrication control failure, secondary control is performed on the wind turbine bearing lubrication system.

7. The method for analyzing low-probability failure of wind turbine bearing lubrication based on evidence theory according to claim 6 is characterized in that: The determining, based on the first bearing image, the second bearing image and the third bearing image, a probability of bearing lubrication control failure includes: Performing image feature extraction based on the first bearing image to obtain a first image feature; Performing image feature extraction based on the second bearing image to obtain a second image feature; Performing image feature extraction based on the third bearing image to obtain a third image feature; determining a first similarity between the third image feature and the first image feature, and determining a second similarity between the third image feature and the second image feature; The probability of bearing lubrication control failure is determined according to the maximum similarity and the minimum similarity among the first similarities and the maximum similarity among the second similarities.