A method, device, equipment and medium for monitoring fan blade faults

Abstract

The present application discloses a method, device, equipment and medium for monitoring fan blade faults, comprising the following steps: obtaining the measured noise value of the fan blades during a sampling period; obtaining a monitoring image of the fan blades, and obtaining the blade defect value based on the monitoring image; inputting the measured noise value and the blade defect value into a preset blade fault warning model to obtain the blade fault warning value. The present application has the advantages of being able to accurately detect the degree of potential fault hazards, facilitating operating personnel to promptly discover blade defects and take shutdown measures to prevent accidents, and facilitating maintenance personnel to reasonably arrange maintenance plans.

Description

Technical Field

[0001] The present application relates to the field of wind turbine monitoring technology, and in particular to a method, device, equipment and medium for monitoring wind turbine blade failures. Background Art

[0002] Wind turbine blades are one of the core components of wind turbines. They work at high altitudes and in all-weather conditions, bearing heavy loads and operating in harsh environments. They are subject to erosion from natural environments such as wind, sun, rain, lightning strikes, and corrosion. Constant erosion by various media will have a huge impact on the life of the blades. Therefore, it is necessary to conduct online monitoring of the wind turbine blades during operation to provide early warning, so as to help maintenance personnel promptly repair wind turbine blades with potential fault hazards.

[0003] However, the existing fan blade fault monitoring method can only detect the existence of potential faults, but cannot accurately quantify the degree of potential faults. When there are many fan blades that need to be repaired, it is difficult for maintenance personnel to reasonably arrange the maintenance plan according to the degree of potential faults. This may cause fan blades with a higher degree of potential faults to miss the best maintenance time and cause major failures, or even fail to operate, causing huge economic losses. Summary of the invention

[0004] The main purpose of the present application is to provide a fan blade fault monitoring method, device, equipment and medium, aiming to solve the technical problem that the existing fan blade fault monitoring method is difficult to accurately detect the degree of potential fault hazards.

[0005] To achieve the above object, the present application provides a method for monitoring fan blade failure, comprising the following steps:

[0006] Obtain the measured noise value of the fan blades during the sampling period;

[0007] Acquire a monitoring image of a wind turbine blade, and obtain a blade defect value based on the monitoring image;

[0008] The measured noise value and blade defect value are input into a preset blade fault warning model to obtain a blade fault warning value.

[0009] Optionally, obtaining a monitoring image of a wind turbine blade, and obtaining a blade defect value according to the monitoring image, includes:

[0010] Acquire a first image of the fan blade; wherein the first image is an image acquired based on a frontal perspective of a rotation plane of the fan blade;

[0011] According to the first image, a first deformation degree ε1 of the fan blade is obtained; wherein the first deformation degree ε1 is a degree of deformation of the fan blade along a rotation direction of the fan blade;

[0012] According to the first image, a surface cracking degree R of the fan blade is obtained;

[0013] Acquire a second image of the fan blade; wherein the second image is an image acquired based on a side view of a rotation plane of the fan blade;

[0014] According to the second image, a second deformation degree ε2 of the fan blade is obtained; wherein the second deformation degree is the degree of deformation of the fan blade along the normal direction of the fan blade rotation direction;

[0015] The blade defect value F is obtained according to the first deformation degree ε1, the surface cracking degree R and the second deformation degree ε2.

[0016] Optionally, obtaining a first deformation degree ε1 of the fan blade according to the first image includes:

[0017] Comparing the first image with a preset first standard image to identify whether there is first deformation information; wherein the first standard image is a front image of a fan blade without deformation, and the first deformation information includes a first deformation area of ​​the fan blade corresponding to a rotation direction of the fan blade;

[0018] If it exists, obtain the deformation area S1 of the first deformation area;

[0019] Identify the angle θ between the line connecting the first offset point to the reference center point and the line connecting the first theoretical point to the reference center point in the first deformation region; wherein the first offset point is the offset position point after the end point of the fan blade is deformed, the first theoretical point is the normal position point of the end point of the fan blade without deformation, and the reference center point is the center point of the annular array of multiple fan blades;

[0020] According to the deformation area S1 and the angle θ, the first deformation degree ε1 of the fan blade is obtained. The expression of ε1 is:

[0021] ε1=K1*S1+K2*θ;

[0022] Wherein, K1 is the first adjustment coefficient, and K2 is the second adjustment coefficient.

[0023] Optionally, obtaining a surface cracking degree R of a wind turbine blade according to the first image includes:

[0024] According to the first image, a surface crack length L of the fan blade is obtained;

[0025] According to the first image, a surface crack depth H of the fan blade is obtained;

[0026] According to the surface crack length L and the surface crack depth H, the surface cracking degree R is obtained. The expression of R is:

[0027] R = K3*L*H;

[0028] Wherein, K3 is the third adjustment coefficient.

[0029] Optionally, obtaining a second deformation degree ε2 of the fan blade according to the second image includes:

[0030] Comparing the second image with a preset second standard image to identify whether there is second deformation information; wherein the second standard image is a side image of a fan blade without deformation, and the second deformation information includes a second deformation area corresponding to the normal of the fan blade along the rotation direction of the fan blade;

[0031] If it exists, identify the bending point and the second offset point in the second deformation area; wherein the bending point is the bending position point after the fan blade is deformed, and the second offset point is the offset position point after the end point of the fan blade is deformed;

[0032] Connect the bending point, the second offset point and the second theoretical point to obtain a triangular area;

[0033] The area S2 of the triangular region is obtained to obtain the second deformation degree ε2, and the expression of ε2 is:

[0034] ε2=K4*S2;

[0035] Wherein, K4 is the fourth adjustment coefficient.

[0036] Optionally, the blade defect value F is expressed as:

[0037] F = w1*ε1+w2*ε2+w3*R;

[0038] Wherein, w1 is the first weight coefficient, w2 is the second weight coefficient, and w3 is the third weight coefficient. Optionally, the expression of the blade fault warning model is:

[0039] Q = K5*(D-D')+K6*F;

[0040] Wherein, Q is the blade fault warning value, D is the measured noise value, D' is the standard noise value, K5 is the fifth adjustment coefficient, and K6 is the sixth adjustment coefficient.

[0041] To achieve the above objectives, the present application also provides a fan blade fault monitoring device, comprising:

[0042] A noise value acquisition module is used to obtain the measured noise value of the fan blades during a sampling period;

[0043] A defect value acquisition module is used to acquire a monitoring image of a wind turbine blade and acquire a blade defect value based on the monitoring image;

[0044] The evaluation module is used to input the measured noise value and the blade defect value into a preset blade fault warning model to obtain a blade fault warning value.

[0045] To achieve the above objectives, the present application also provides a computer device, which includes a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the above method.

[0046] To achieve the above objectives, the present application also provides a computer-readable storage medium, on which a computer program is stored, and a processor executes the computer program to implement the above method.

[0047] The beneficial effects that this application can achieve are as follows:

[0048] The present application obtains the measured noise value of the fan blade, which can reflect the operating status of the fan blade. When the fan blade operates abnormally due to internal faults or surface defects, the measured noise value will be different from the normal sound, so as to judge whether the blade has a fault based on whether abnormal noise is detected. However, due to environmental factors, the measured noise value may not be accurate enough. Therefore, in order to improve the accuracy of the detection data, the present application also combines the monitoring image of the fan blade to evaluate and obtain the blade defect value. The blade defect value can accurately characterize the degree of surface defects of the fan blade and is less affected by environmental factors. At the same time, the measured noise value and the blade defect value are input into the preset blade fault warning model to obtain the blade fault warning value, which can quantitatively assess the degree of fan blade fault and improve the detection accuracy, which is conducive to auxiliary maintenance personnel to judge the maintenance sequence priority according to the size of the blade fault warning value, so as to reasonably formulate a maintenance plan. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] In order to more clearly illustrate the specific embodiments of the present application or the technical solutions in the prior art, the following is a brief introduction to the drawings required for the specific embodiments or the prior art description. In all drawings, similar elements or parts are generally identified by similar reference numerals. In the drawings, the elements or parts are not necessarily drawn according to the actual scale.

[0050] Figure 1 A schematic flow chart of a method for monitoring fan blade failure in an embodiment of the present application;

[0051] Figure 2 is a schematic diagram of a first standard image in an embodiment of the present application;

[0052] Figure 3 Schematic diagram of the principle of calculating the first deformation degree based on the first image in an embodiment of the present application;

[0053] Figure 4 is a schematic diagram of a second standard image in an embodiment of the present application;

[0054] Figure 5 It is a schematic diagram of the principle of calculating the second deformation degree based on the second image in an embodiment of the present application.

[0055] The realization of the purpose, functional features and advantages of this application will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0056] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0057] It should be noted that all directional indications in the embodiments of the present application (such as up, down, left, right, front, back, etc.) are only used to explain the relative position relationship, movement status, etc. between the components in a certain specific posture. If the specific posture changes, the directional indication will also change accordingly.

[0058] In this application, unless otherwise clearly specified and limited, the terms "connection", "fixation", etc. should be understood in a broad sense. For example, "fixation" can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium, it can be the internal connection of two elements or the interaction relationship between two elements, unless otherwise clearly defined. For ordinary technicians in this field, the specific meanings of the above terms in this application can be understood according to specific circumstances.

[0059] In addition, if there are descriptions involving "first", "second", etc. in the embodiments of the present application, the descriptions of "first", "second", etc. are only used for descriptive purposes and cannot be understood as indicating or implying their relative importance or implicitly indicating the number of technical features indicated. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In addition, the meaning of "and / or" appearing in the full text includes three parallel schemes. Taking "A and / or B" as an example, it includes scheme A, or scheme B, or a scheme that satisfies both A and B. In addition, the technical solutions between the various embodiments can be combined with each other, but it must be based on the ability of ordinary technicians in the field to implement. When the combination of technical solutions is contradictory or cannot be implemented, it should be considered that such a combination of technical solutions does not exist and is not within the scope of protection required by this application.

[0060] Example 1

[0061] Reference Figure 1-Figure 5 This embodiment provides a method for monitoring fan blade failure, comprising the following steps:

[0062] Obtain the measured noise value of the fan blades during the sampling period;

[0063] Acquire a monitoring image of a wind turbine blade, and obtain a blade defect value based on the monitoring image;

[0064] The measured noise value and blade defect value are input into a preset blade fault warning model to obtain a blade fault warning value.

[0065] In this embodiment, by obtaining the measured noise value of the fan blade, the measured noise value can reflect the operating status of the fan blade. When the fan blade operates abnormally due to internal faults or surface defects, the measured noise value will be different from the normal sound, so that whether the blade has a fault can be judged based on whether abnormal noise is detected. However, due to environmental factors (such as bad weather), the measured noise value may not be accurate enough. Therefore, in order to improve the accuracy of the detection data, this embodiment also combines the monitoring image of the fan blade to evaluate and obtain the blade defect value. The blade defect value can accurately characterize the degree of surface defects of the fan blade and is less affected by environmental factors. At the same time, the measured noise value and the blade defect value are input into the preset blade fault warning model, so that the blade fault warning value can be obtained, and the degree of fan blade failure can be quantitatively assessed. The detection accuracy is improved, which is beneficial for auxiliary maintenance personnel to judge the maintenance sequence priority according to the size of the blade fault warning value, so as to reasonably formulate a maintenance plan.

[0066] As an optional implementation manner, obtaining a monitoring image of a wind turbine blade and obtaining a blade defect value according to the monitoring image includes:

[0067] Acquire a first image of the fan blade; wherein the first image is an image acquired based on a frontal perspective of a rotation plane of the fan blade;

[0068] According to the first image, a first deformation degree ε1 of the fan blade is obtained; wherein the first deformation degree ε1 is a degree of deformation of the fan blade along a rotation direction of the fan blade;

[0069] According to the first image, a surface cracking degree R of the fan blade is obtained;

[0070] Acquire a second image of the fan blade; wherein the second image is an image acquired based on a side view of a rotation plane of the fan blade;

[0071] According to the second image, a second deformation degree ε2 of the fan blade is obtained; wherein the second deformation degree is the degree of deformation of the fan blade along the normal direction of the fan blade rotation direction;

[0072] The blade defect value F is obtained according to the first deformation degree ε1, the surface cracking degree R and the second deformation degree ε2.

[0073] In this embodiment, since there are many types of surface defects on the fan blades, mainly including surface cracks and blade deformation, the end part of the fan blade is subjected to greater forces and is greatly affected by environmental factors. Therefore, the blade deformation here is mainly a local deformation occurring at the end of the blade, and the blade deformation is divided into circumferential deformation and axial deformation (both can exist at the same time). Circumferential deformation refers to the deformation of the blade along the direction of rotation of the blade, and axial deformation refers to the deformation of the blade along the normal direction of the direction of rotation of the blade. Therefore, here, a first image is first acquired based on the front view of the fan blade, and the first deformation degree ε1 and the surface cracking degree R of the blade can be calculated respectively through the first image. The circumferential deformation degree of the fan blade can be characterized by the first deformation degree ε1, and then the second image is acquired based on the side view of the fan blade, and the second deformation degree ε2 of the blade can be calculated. The second deformation degree ε2 can be characterized by the axial deformation degree of the fan blade. Therefore, this embodiment can accurately evaluate the total blade defect value F by quantifying the degree of surface cracks and blade deformation respectively, thereby ensuring the accuracy of the blade fault warning value.

[0074] It should be noted that a traditional fan blade generally has three blades and are evenly distributed in a circular array. The first image can display the contour information of the front of the three fan blades. By extracting the contour information of the fan blades, the corresponding first deformation degree ε1 can be calculated. Here, the first deformation degree ε1 should be the sum of the deformation degrees of the three fan blades in the circumferential direction; since the second image is an image of the fan blade from the side view, and the three fan blades cannot all appear in a vertical state in the second image, multiple second images should be obtained here, and each second image shows at least one of the fan blades in a vertical state, so that the contour information of the axial deformation of the fan blades can be accurately extracted to ensure data accuracy. Similarly, the second deformation degree ε2 here should be the sum of the deformation degrees of the three fan blades in the axial direction.

[0075] As an optional implementation manner, obtaining a first deformation degree ε1 of the fan blade according to the first image includes:

[0076] Comparing the first image with a preset first standard image to identify whether there is first deformation information; wherein the first standard image is a front image of a fan blade without deformation, and the first deformation information includes a first deformation area of ​​the fan blade corresponding to a rotation direction of the fan blade;

[0077] If it exists, obtain the deformation area S1 of the first deformation area;

[0078] Identify the angle θ between the line connecting the first offset point to the reference center point and the line connecting the first theoretical point to the reference center point in the first deformation region; wherein the first offset point is the offset position point after the end point of the fan blade is deformed, the first theoretical point is the normal position point of the end point of the fan blade without deformation, and the reference center point is the center point of the annular array of multiple fan blades;

[0079] According to the deformation area S1 and the angle θ, the first deformation degree ε1 of the fan blade is obtained. The expression of ε1 is:

[0080] ε1=K1*S1+K2*θ;

[0081] Wherein, K1 is the first adjustment coefficient, and K2 is the second adjustment coefficient.

[0082] In this embodiment, when calculating the first deformation degree ε1, the first image is compared with the first standard image, so that the contrast difference can be identified. When it is detected that there is no first deformation information, the first deformation degree ε1 is defaulted to 0. When it exists, there are two parameter factors affecting the size of the first deformation degree ε1, namely the deformation area S1 and the angle θ, according to the deformation situation. The deformation area S1 is the blade area corresponding to a section of the blade end that is deformed. When calculating the deformation area S1, a bending line between a section of the blade end that is deformed and an area that is not deformed is first constructed. The bending line and the section of the blade end that is deformed form a closed figure. The area of ​​the calculated closed figure is the deformation area S1. Then the angle θ can characterize the distance of the blade end from the original position when it is deformed. Here, a line connecting the first offset point to the reference center point and a line connecting the first theoretical point to the reference center point in the first deformation area can be constructed. The reference center point and the first theoretical point are both fixed points. Calculating the angle θ between the two connecting lines can represent the offset size of the first offset point, and the deformation area S1 and the angle θ are both positively correlated with the first deformation degree ε1. Based on the above expression of ε1, there may be a situation where the deformation area S1 is small but the angle θ is large, or the angle θ is small but the deformation area S1 is large, both of which will lead to a larger first deformation degree ε1. The deformation area S1 and the angle θ are parameters of different units, so they are converted by the first adjustment coefficient K1 and the second adjustment coefficient K2 respectively, so that the two can be superimposed on each other. In addition, according to the degree of influence of the deformation area S1 and the angle θ on the normal operation of the wind turbine blades, the first adjustment coefficient K1 and the second adjustment coefficient K2 also include corresponding weight coefficients. Therefore, no matter how the deformation area S1 and the angle θ change, they can be accurately reflected in the value change of the first deformation degree ε1, so that the first deformation degree ε1 can be accurately calculated to ensure the accuracy of the blade deformation detection data.

[0083] As an optional implementation manner, obtaining the surface cracking degree R of the wind turbine blade according to the first image includes:

[0084] According to the first image, a surface crack length L of the fan blade is obtained;

[0085] According to the first image, a surface crack depth H of the fan blade is obtained;

[0086] According to the surface crack length L and the surface crack depth H, the surface cracking degree R is obtained. The expression of R is:

[0087] R = K3*L*H;

[0088] Wherein, K3 is the third adjustment coefficient.

[0089] In this embodiment, since the surface cracks of the blade mostly occur on the front surface of the blade with width, and the length and depth of the surface cracks of the blade will affect the hidden dangers of blade breakage and deformation, when calculating the surface cracking degree R, the surface crack length L can be estimated through the stripe information on the corresponding blade in the first image. At the same time, the first image here should be a 3D depth image, so that the corresponding surface crack depth H can be estimated. Since there may be cracks of different depths in the crack length direction, the maximum crack depth is used as the surface crack depth H. The surface cracking degree R can be accurately calculated based on the product of the two.

[0090] It should be noted that the third adjustment coefficient is set here to adjust the value of the final surface cracking degree R, so that when the blade defect value F is subsequently calculated, the surface cracking degree R can be superimposed with parameters of other different units to accurately obtain the final blade defect value F.

[0091] As an optional implementation manner, obtaining a second deformation degree ε2 of the wind turbine blade according to the second image includes:

[0092] Comparing the second image with a preset second standard image to identify whether there is second deformation information; wherein the second standard image is a side image of a fan blade without deformation, and the second deformation information includes a second deformation area corresponding to the normal of the fan blade along the rotation direction of the fan blade;

[0093] If it exists, identify the bending point and the second offset point in the second deformation area; wherein the bending point is the bending position point after the fan blade is deformed, and the second offset point is the offset position point after the end point of the fan blade is deformed;

[0094] Connect the bending point, the second offset point and the second theoretical point to obtain a triangular area;

[0095] The area S2 of the triangular region is obtained to obtain the second deformation degree ε2, and the expression of ε2 is:

[0096] ε2=K4*S2;

[0097] Wherein, K4 is the fourth adjustment coefficient.

[0098] In this embodiment, when calculating the second deformation degree ε2, since the second image shows the contour of the fan blade in the thickness direction and its contour area is small, the second deformation degree ε2 cannot be characterized by the deformation area. Therefore, the bending position of the fan blade after deformation is fitted into a point, namely the bending point, and then the second offset point position is identified according to the contrast difference between the second image and the second standard image. The second theoretical point is a fixed point, and the bending point and the second offset point are variables. Therefore, the second deformation degree ε2 can be characterized by calculating the area S2 of the triangular area surrounded by the bending point, the second offset point and the second theoretical point. The farther the second offset point or the bending point is from the second theoretical point, the larger the area S2 will be, and the larger the second deformation degree ε2 will be, so that the second deformation degree ε2 can be accurately calculated. Similarly, the fourth adjustment coefficient K4 in the above formula is used to adjust the value of the final second deformation degree ε2, so that when the blade defect value F is subsequently calculated, the second deformation degree ε2 can be superimposed with parameters of other different units to accurately obtain the final blade defect value F.

[0099] As an optional implementation, the blade defect value F is expressed as:

[0100] F = w1*ε1+w2*ε2+w3*R;

[0101] Wherein, w1 is the first weight coefficient, w2 is the second weight coefficient, and w3 is the third weight coefficient.

[0102] In this embodiment, since the first deformation degree ε1, the second deformation degree ε2 and the surface cracking degree R have different degrees of influence on blade failure, the corresponding degrees of influence can be expressed by assigning weight coefficients corresponding to the three parameters respectively. The data of the blade defect value F finally obtained is more authentic and has greater reference accuracy.

[0103] As an optional implementation, the blade failure warning model is expressed as:

[0104] Q = K5*(D-D')+K6*F;

[0105] Wherein, Q is the blade fault warning value, D is the measured noise value, D' is the standard noise value, K5 is the fifth adjustment coefficient, and K6 is the sixth adjustment coefficient.

[0106] In this embodiment, the degree of noise abnormality is represented by the difference between the measured noise value D and the standard noise value D'. By setting the fifth adjustment coefficient K5 and the sixth adjustment coefficient K6, the blade defect value F and the noise difference can be superimposed to jointly determine the size of the blade fault warning value. The data has high accuracy and is of reference and guiding significance.

[0107] Example 2

[0108] Based on the same inventive concept as the above-mentioned embodiment, this embodiment further provides a fan blade fault monitoring device, comprising:

[0109] A noise value acquisition module is used to obtain the measured noise value of the fan blades during a sampling period;

[0110] A defect value acquisition module is used to acquire a monitoring image of a wind turbine blade and acquire a blade defect value based on the monitoring image;

[0111] The evaluation module is used to input the measured noise value and the blade defect value into a preset blade fault warning model to obtain a blade fault warning value.

[0112] The relevant explanations and examples of each module in the device of this embodiment can refer to the method of the aforementioned embodiment, and will not be repeated here.

[0113] Example 3

[0114] Based on the same inventive concept as the above-mentioned embodiment, this embodiment provides a computer device, which includes a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the above-mentioned method.

[0115] Example 4

[0116] Based on the same inventive concept as the aforementioned embodiment, this embodiment provides a computer-readable storage medium, on which a computer program is stored, and a processor executes the computer program to implement the aforementioned method.

[0117] The above are only preferred embodiments of the present application, and are not intended to limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made using the contents of the present application specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present application.

Claims

1. A method for monitoring fan blade faults, characterized in that: The following steps are involved: Obtain the measured noise value of the fan blades during the sampling period; Acquire a monitoring image of the fan blade, and acquire a blade defect value according to the monitoring image; including: acquiring a first image of the fan blade; wherein the first image is an image acquired based on a front view of a rotation plane of the fan blade; acquiring a first deformation degree ε1 of the fan blade according to the first image; wherein the first deformation degree ε1 is a degree of deformation of the fan blade along a rotation direction of the fan blade; acquiring a surface cracking degree R of the fan blade according to the first image; acquiring a second image of the fan blade; wherein the second image is an image acquired based on a side view of a rotation plane of the fan blade; acquiring a second deformation degree ε2 of the fan blade according to the second image; wherein the second deformation degree is a degree of deformation of the fan blade along a normal to the rotation direction of the fan blade; acquiring a blade defect value F according to the first deformation degree ε1, the surface cracking degree R and the second deformation degree ε2; The measured noise value and the blade defect value are input into a preset blade fault warning model to obtain a blade fault warning value.

2. A fan blade fault monitoring method according to claim 1, characterized in that: The step of acquiring a first deformation degree ε1 of the fan blade according to the first image includes: Comparing the first image with a preset first standard image to identify whether there is first deformation information; wherein the first standard image is a front image of a fan blade without deformation, and the first deformation information includes a first deformation area of ​​the fan blade corresponding to the rotation direction of the fan blade; If it exists, obtaining the deformation area S1 of the first deformation region; Identify the angle θ between the line connecting the first offset point to the reference center point and the line connecting the first theoretical point to the reference center point in the first deformation area; wherein the first offset point is the offset position point after the end point of the fan blade is deformed, the first theoretical point is the normal position point of the end point of the fan blade without deformation, and the reference center point is the center point of the annular array of multiple fan blades; According to the deformation area S1 and the angle θ, the first deformation degree ε1 of the fan blade is obtained, and the expression of ε1 is: ε1=K1*S1+K2*θ; Wherein, K1 is the first adjustment coefficient, and K2 is the second adjustment coefficient.

3. A fan blade fault monitoring method according to claim 1, characterized in that: The step of obtaining a surface cracking degree R of the wind turbine blade according to the first image includes: Acquire a surface crack length L of the wind turbine blade according to the first image; Acquire a surface crack depth H of the wind turbine blade according to the first image; According to the surface crack length L and the surface crack depth H, the surface cracking degree R is obtained, and the expression of R is: R = K3*L*H; Wherein, K3 is the third adjustment coefficient.

4. A fan blade fault monitoring method according to claim 1, characterized in that: The step of acquiring a second deformation degree ε2 of the fan blade according to the second image includes: Comparing the second image with a preset second standard image to identify whether second deformation information exists; wherein the second standard image is a side image of a fan blade without deformation, and the second deformation information includes a second deformation area of ​​the fan blade corresponding to the normal direction of the fan blade along the rotation direction of the fan blade; If it exists, identify the bending point and the second offset point in the second deformation area; wherein the bending point is the bending position point of the fan blade after deformation, and the second offset point is the offset position point of the end point of the fan blade after deformation; Connect the bending point, the second offset point and the second theoretical point to obtain a triangular area; The area S2 of the triangular region is obtained to obtain the second deformation degree ε2, and the expression of ε2 is: ε2=K4*S2; Wherein, K4 is the fourth adjustment coefficient.

5. A fan blade fault monitoring method according to any one of claims 1 to 4, characterized in that: The expression of the blade defect value F is: F = w1*ε1+w2*ε2+w3*R; Wherein, w1 is the first weight coefficient, w2 is the second weight coefficient, and w3 is the third weight coefficient.

6. A fan blade fault monitoring method as claimed in claim 5, characterized in that: The expression of the blade failure early warning model is: Q = K5*(D-D')+K6*F; Wherein, Q is the blade fault warning value, D is the measured noise value, D' is the standard noise value, K5 is the fifth adjustment coefficient, and K6 is the sixth adjustment coefficient.

7. A fan blade fault monitoring device, characterized in that: include: A noise value acquisition module is used to obtain the measured noise value of the fan blades during a sampling period; A defect value acquisition module, used for acquiring a monitoring image of the wind blade, and acquiring a blade defect value according to the monitoring image; comprising: acquiring a first image of the wind blade; wherein the first image is an image acquired based on a front view of a rotation plane of the wind blade; acquiring a first deformation degree ε1 of the wind blade according to the first image; wherein the first deformation degree ε1 is the degree to which the wind blade is deformed along the rotation direction of the wind blade; acquiring a surface cracking degree R of the wind blade according to the first image; acquiring a second image of the wind blade; wherein the second image is an image acquired based on a side view of the rotation plane of the wind blade; acquiring a second deformation degree ε2 of the wind blade according to the second image; wherein the second deformation degree is the degree to which the wind blade is deformed along the normal direction of the rotation direction of the wind blade; acquiring a blade defect value F according to the first deformation degree ε1, the surface cracking degree R and the second deformation degree ε2; The evaluation module is used to input the measured noise value and the blade defect value into a preset blade fault warning model to obtain a blade fault warning value.

8. A computer device, characterized in that: The computer device comprises a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the method according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and the processor executes the computer program to implement the method according to any one of claims 1 to 6.

Images