CN114881997A - Wind turbine generator defect assessment method and related equipment - Google Patents

Abstract

The present application discloses a defect assessment method for a wind turbine and related equipment. The method includes: identifying a detection picture of a target wind turbine to obtain defect parameters of the target defect in the target wind turbine, wherein the defect parameters include defect type, defect absolute position and defect size characteristic parameters; The absolute position of the defect and the weighting coefficient corresponding to the above-mentioned characteristic parameter of defect size; the probability of defect risk is calculated based on the above-mentioned defect type, the above-mentioned absolute position of the defect, the above-mentioned characteristic parameter of defect size and its corresponding weighting coefficient. The method provided in the embodiment of the present application comprehensively considers the defect type, defect location, and defect size to describe the defects of multiple components with multiple indicators. An AHP-based defect risk assessment method for wind turbines is proposed, which can be used to scientifically formulate maintenance plans for wind turbines.

Description

A kind of wind turbine defect assessment method and related equipment

technical field

This specification relates to the field of wind turbines, and more particularly, the present invention relates to a method for evaluating defects of wind turbines and related equipment.

Background technique

In the equipment management of wind power plants, the safe operation of wind turbines is the primary consideration. However, wind power plants generally occupy a wide area, with remote terrain and complex terrain. The daily workload of equipment operation and maintenance is large, and the operation status of the equipment is difficult to monitor, which is prone to errors.

In the traditional technology, the inspection of wind turbines is usually carried out by means of telescopes, high-power cameras on the ground, hanging baskets and other equipment. In addition, most of the existing wind turbine defect identification only identifies and judges the defect of a certain component of the wind turbine independently, without considering the influence of the defect type, location, and size on the severity of the defect, and lacks a unified defect risk assessment standard. Scientifically formulate the maintenance time node and cycle of each component of the wind turbine.

SUMMARY OF THE INVENTION

A series of concepts in simplified form have been introduced in the Summary section, which are described in further detail in the Detailed Description section. The Summary of the Invention section of the present invention is not intended to attempt to limit the key features and essential technical features of the claimed technical solution, nor is it intended to attempt to determine the protection scope of the claimed technical solution.

In order to scientifically evaluate the defects of wind turbines, in the first aspect, the present invention proposes a method for evaluating defects of wind turbines, and the above method includes:

Identifying the inspection picture of the target wind turbine to obtain defect parameters of the target defect in the above-mentioned target wind turbine, wherein the above-mentioned defect parameters include defect type, defect absolute position and defect size characteristic parameters;

Obtain the weighting coefficients corresponding to the above-mentioned defect type, the above-mentioned absolute position of the defect, and the above-mentioned characteristic parameters of the above-mentioned defect size;

The defect risk probability is calculated based on the above-mentioned defect type, the above-mentioned absolute position of the defect, the above-mentioned characteristic parameter of the defect size and its corresponding weighting coefficient.

Optionally, the above method further includes:

Obtain the drone coordinate information, shooting parameter information and wind turbine size information of the target drone, wherein the shooting parameter information includes the angle information and camera focal length information corresponding to the target drone and the target camera carried by the target drone. is the camera used to take the above detection picture;

The coordinate conversion operation is performed based on the above-mentioned UAV coordinate information, the above-mentioned shooting parameter information and the above-mentioned wind turbine size information to obtain the above-mentioned absolute position of the defect, wherein the absolute position of the defect includes the position in the length direction of the defect and the position in the width direction of the defect.

Optionally, the above method further includes:

Obtain the defective pixel area of the above target defect;

Obtain the part length of the part corresponding to the above target defect;

The above-mentioned defect size characteristic parameters are calculated according to the above-mentioned part length and the above-mentioned defect area.

Optionally, the above method further includes:

Identify the above-mentioned detection pictures based on the target full convolutional neural network model to obtain the above-mentioned defect types, wherein the above-mentioned target full-convolutional neural network model is obtained by training the training pictures with defect types marked by labelme, and the above-mentioned defect types at least include dirty at least one of contamination, abrasion, cracking, delamination, cracks and lightning strikes.

Optionally, obtaining the weighting coefficients corresponding to the defect type, the absolute position of the defect, and the characteristic parameter of the defect size above, including:

The above-mentioned acquisition of the above-mentioned defect type, the above-mentioned absolute position of the defect, and the above-mentioned characteristic parameter of the defect size are used as evaluation parameters to carry out an expert scoring operation to obtain relative importance information, wherein the above-mentioned relative importance information is the relative importance degree information between each two defect parameters ;

Build an evaluation matrix based on the above relative importance information;

Obtain the maximum characteristic root and the average random consistency index corresponding to the evaluation matrix, wherein the average random consistency index is determined according to the order of the evaluation matrix;

Calculate the random consistency index according to the above largest characteristic root and the above average random consistency index;

When the random consistency index is smaller than the preset consistency index, the weighting coefficients corresponding to the defect type, the absolute position of the defect, and the characteristic parameter of the defect size are calculated based on the evaluation matrix.

Optionally, the above-mentioned weighting coefficients corresponding to the above-mentioned defect type, the above-mentioned absolute position of the defect, and the above-mentioned characteristic parameter of the defect size are calculated based on the above-mentioned evaluation matrix, including:

The weighting coefficients corresponding to the above-mentioned defect types, the above-mentioned defect absolute positions and the above-mentioned defect size characteristic parameters are calculated according to the following formula:

为上述加权系数，W_i为上述评估矩阵中各行元素乘积的

次方，n为上述评估矩阵对应的阶次，∑W_i为所有∑W_i的和。In the formula,

is the above weighting coefficient, W _i is the product of the elements of each row in the above evaluation matrix

power, n is the order corresponding to the above evaluation matrix, ∑W _i is the sum of all ∑W _i .

Optionally, the above method further includes:

Defect risk levels and corresponding preset maintenance measures are determined according to the above-mentioned defect risk probability and preset maintenance strategy table.

In a second aspect, the present application also proposes a wind turbine defect assessment device, comprising:

an identification unit, configured to identify the detection picture of the target wind turbine to obtain defect parameters of the target defect in the target wind turbine, wherein the defect parameters include defect type, defect absolute position and defect size characteristic parameters;

an obtaining unit, configured to obtain the weighting coefficient corresponding to the defect type, the absolute position of the defect and the characteristic parameter of the defect size;

A calculation unit, configured to calculate the defect risk probability based on the defect type, the absolute position of the defect, the characteristic parameter of the defect size and its corresponding weighting coefficient.

A third aspect, an electronic device, comprising: a memory, a processor, and a computer program stored in the memory and running on the processor, the processor being used to execute the computer program stored in the memory to implement the above-mentioned first The steps of any one of the wind turbine defect assessment methods in one aspect.

In a fourth aspect, the present invention further provides a computer-readable storage medium on which a computer program is stored, and when the computer program is executed by a processor, implements any one of the above-mentioned wind turbine defect assessment methods in the first aspect.

To sum up, a method for evaluating a defect of a wind turbine proposed in an embodiment of the present application includes: identifying a detection picture of a target wind turbine to obtain a defect parameter of the target defect in the target wind turbine, wherein the defect parameter includes a defect type, a defect Absolute position and defect size characteristic parameters; obtain the weighting coefficients corresponding to the above-mentioned defect types, the above-mentioned defect absolute positions and the above-mentioned defect size characteristic parameters; calculate based on the above-mentioned defect types, the above-mentioned defect absolute positions, the above-mentioned defect size characteristic parameters and their corresponding weighting coefficients Defect risk probability. The method provided in the embodiment of the present application comprehensively considers the defect type, defect location, and defect size to describe the defects of multiple components with multiple indicators, thereby making the description of the defects of the wind turbine more comprehensive and objective. A defect risk assessment method for wind turbines based on AHP is proposed, which comprehensively considers defect type, defect location and defect size to determine the defect risk level, which can be used to scientifically formulate the maintenance plan of wind turbines.

The wind turbine defect assessment method of the present invention, and other advantages, objectives and features of the present invention will be reflected in part by the following description, and in part will be understood by those skilled in the art through the study and practice of the present invention.

Description of drawings

Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The drawings are for the purpose of illustrating preferred embodiments only and are not to be considered limiting of the description. Also, the same components are denoted by the same reference numerals throughout the drawings. In the attached image:

1 is a schematic flowchart of a method for evaluating a defect of a wind turbine according to an embodiment of the present application;

FIG. 2 is a schematic structural diagram of a wind turbine according to an embodiment of the present application;

3 is a schematic diagram of a coordinate transformation principle provided by an embodiment of the present application;

FIG. 4 is a schematic diagram of another coordinate transformation principle provided by an embodiment of the present application;

5 is a schematic structural diagram of a wind turbine blade according to an embodiment of the present application;

6 is a schematic structural diagram of another wind turbine blade according to an embodiment of the present application;

FIG. 7 is a schematic structural diagram of another wind turbine blade according to an embodiment of the present application;

FIG. 8 is a schematic structural diagram of still another wind turbine blade according to an embodiment of the present application;

Fig. 9 is a kind of wind turbine defect assessment device provided by the embodiment of the present application;

FIG. 10 is a schematic structural diagram of an electronic device for evaluating a defect of a wind turbine according to an embodiment of the present application.

Detailed ways

The terms "first", "second", "third", "fourth", etc. (if any) in the description and claims of this application and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It is to be understood that data so used may be interchanged under appropriate circumstances so that the embodiments described herein can be practiced in sequences other than those illustrated or described herein. Furthermore, the terms "comprising" and "having" and any variations thereof, are intended to cover non-exclusive inclusion, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those expressly listed Rather, those steps or units may include other steps or units not expressly listed or inherent to these processes, methods, products or devices. The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, but not all of the embodiments.

Please refer to FIG. 1 , which is a schematic flowchart of a method for evaluating a defect of a wind turbine in an embodiment of the present application. The method includes:

S110. Identify the detection picture of the target wind turbine to obtain defect parameters of the target defect in the above-mentioned target wind turbine, wherein the above-mentioned defect parameters include defect type, defect absolute position and defect size characteristic parameters;

Exemplarily, the inspection pictures of the target wind turbine are identified by an intelligent algorithm, the defects in the parts of the wind turbine are obtained, and the defect parameters of the target defect are obtained. The defect parameters include the type of the defect, and the type of the defect can be dirt, wear , cracking, delamination, crack, lightning strike one or more, the absolute position of the defect refers to which part of the wind turbine the defect is on, and the specific position on the component, as shown in Figure 2, the wind turbine, the main Including components such as blade tip 104, blade 105, hub 108, nacelle 106, and tower 107, the characteristic parameters of the single size of the defect may include the area of the defect and the specific location of the defect, or a comprehensive parameter of the area and the specific location.

S120. Obtain the weighting coefficients corresponding to the defect type, the absolute position of the defect, and the characteristic parameter of the defect size;

Exemplarily, the type of defect, the location of the defect and the single size characteristics of the defect have different influences on the wind turbine. For example, the severity of oil pollution is lower than that of the blade tip falling off, and cracks appear in the core material of the blade. Regions are less severe than cracks at the tip of the blade or where the blade joins the hub. This method assigns weights to three influencing factors of defect type, defect location, and defect size through the fan components. If the defect is relatively large in the blade tip and hub joint, and relatively small in the nacelle surface and the blade core material area, Then, the defect risk level is calculated according to the defect category weight, location weight, and range weight.

S130: Calculate the defect risk probability based on the defect type, the absolute position of the defect, the characteristic parameter of the defect size, and the corresponding weighting coefficient.

Exemplarily, multiply the defect type, the absolute position of the defect, and the defect size with their corresponding weighting coefficients, and the sum of the products obtained is the defect risk probability, and the defect risk probability F can be calculated by the following formula:

为缺陷类型对应的第一加权系数，f(type)为缺陷类型，

为缺陷绝对位置对应的第二加权系数，f(％L,％C)为缺陷尺寸特征参数，

为缺陷尺寸特征参数对应的第三加权系数，f(S,L)为缺陷尺寸特征参数。

is the first weighting coefficient corresponding to the defect type, f(type) is the defect type,

is the second weighting coefficient corresponding to the absolute position of the defect, f(%L,%C) is the characteristic parameter of the defect size,

is the third weighting coefficient corresponding to the defect size feature parameter, and f(S, L) is the defect size feature parameter.

To sum up, the method provided in the embodiment of the present application comprehensively considers the defect type, defect location, and defect size to describe the defects of multiple components with multiple indicators, thereby making the description of the defects of the wind turbine more comprehensive and objective. A defect risk assessment method for wind turbines based on AHP is proposed, which comprehensively considers defect type, defect location and defect size to determine the defect risk level, which can be used to scientifically formulate the maintenance plan of wind turbines.

In some examples, the above method further includes:

Obtain the drone coordinate information, shooting parameter information and wind turbine size information of the target drone, wherein the shooting parameter information includes the angle information and camera focal length information corresponding to the target drone and the target camera carried by the target drone. is the camera used to take the above detection picture;

The coordinate conversion operation is performed based on the above-mentioned UAV coordinate information, the above-mentioned shooting parameter information and the above-mentioned wind turbine size information to obtain the above-mentioned absolute position of the defect, wherein the absolute position of the defect includes the position in the length direction of the defect and the position in the width direction of the defect.

Exemplarily, the detection picture can be obtained by taking a camera carried by a drone, and specifically, the picture of the fan assembly can be obtained by means of the M300 RTK drone carrying a Zenmuse H20 camera, and the limited The camera gimbal attitude, the rotation angle is between [-5,5], the pitch angle is set to {-90,-60,-30}, and the yaw angle is not required. Build a distributed UAV nest, and conduct automatic inspection through UAV intelligent scheduling algorithm and path planning. The wind turbine mainly includes four parts: blade, nacelle, hub and tower. When controlling the UAV for image acquisition, first fly along the tower of the wind turbine from bottom to top, then fly along the axis of the blade, fly over the top of the lower surface of the blade, and then fly under the blade along the axis of the blade After flying all the blades in sequence, the surface of the blade and the curved surface of the edge connecting the two surfaces, as well as the nacelle, the hub, and the tower can all be photographed. According to the length of the blade and the focal length of the camera on the UAV, the number of blade segments to be detected is divided, and a sample database of wind turbine defects is established, so that it can fully reflect the situation of the wind turbine to be detected.

The picture information is processed according to the obtained picture, as well as the UAV coordinate information, shooting parameter information and wind turbine size information associated with the picture. First, the image pixel position of the defect of the wind turbine is calculated. Calculate the corresponding geographic coordinates with other parameters, and judge the location of the defect on the component with reference to the wind turbine size information. The specific coordinate conversion calculation formula is:

The image coordinate system and camera coordinate system are shown in Figure 3 and Figure 4. The xy plane is the physical coordinate plane of the image, the Xc axis is parallel to the x axis of the image coordinate system, the Yc axis is parallel to the y axis of the image coordinate system, the Zc axis is the optical axis of the camera, which is perpendicular to the image plane, and R(α, β, γ) is the rotation The matrix is the product of the three axial rotation matrices of x, y and z, (α, β, γ) is the attitude angle, T is the translation vector, representing the translation distance on the three axes, L _W is composed of rotation and translation A 4*4 matrix, dx is the size of each pixel on the horizontal axis x, dy is the size of each pixel on the vertical axis y, and f is the camera focal length.

Determine which part of the wind turbine is defective by the coordinates and the three-dimensional model, and then establish the defect position description formula f(%L,%C) according to the length L and width C of the part, where %L and %C are the proportion of the length of the component ( That is, the defect length direction position) and the width ratio (defect width direction position) to describe the defect position.

In order to uniformly describe the defect risk of different types of blades, and to establish the relationship between the defect risk and defect location of the blade more specifically, the blade is usually divided into blade tip, main beam, blade leading edge, blade core material area, blade according to the structure. trailing edge, leaf root. The schematic diagrams of blade structure division are shown in Figures 5 to 8, in which 101 is the blade root, 102 is the front and rear edges of the blade, 103 is the main beam, and 104 is the blade tip.

To sum up, the method proposed in the embodiments of the present application uses the unmanned aerial vehicle platform to realize the detection of fan components, and performs automatic inspection, which can improve the inspection efficiency and detection accuracy. The collected images are converted into coordinates, and the defects are located at specific positions in specific parts. A method combining image recognition and coordinate positioning is proposed, which can not only automatically identify the defects, but also accurately locate the defects. Can be used to guide staff to quickly eliminate defects.

In some examples, the above method further includes:

Obtain the defective pixel area of the above target defect;

Obtain the part length of the part corresponding to the above target defect;

The above-mentioned defect size characteristic parameters are calculated according to the above-mentioned part length and the above-mentioned defect area.

Exemplarily, after the defect is identified, the defect pixel area S is calculated, and the influence of the actual length L of the component is considered to establish a defect size description formula, denoted as f(S, L), and the calculation formula can be:

f(S,L)=S×L

To sum up, in the method proposed in this embodiment of the present application, the product of the defect pixel area and the actual length of the component is used as a characteristic parameter to describe the size of the defect, and not only the size of the defect is considered, but also the influence of the length of the component on the wind turbine, so that the defect The evaluation method is more accurate.

In some examples, the above method further includes:

Identify the above-mentioned detection pictures based on the target full convolutional neural network model to obtain the above-mentioned defect types, wherein the above-mentioned target full-convolutional neural network model is obtained by training the training pictures with defect types marked by labelme, and the above-mentioned defect types at least include dirty at least one of contamination, abrasion, cracking, delamination, cracks and lightning strikes.

Exemplarily, an artificial intelligence algorithm is used to identify defects in the obtained pictures, and a fully convolutional neural network model is specifically used to intelligently identify the defects of the wind turbine. Before defect identification, the target fully convolutional neural network model needs to be trained. First, use the data labeling tool labelme to mark the defect information in the wind turbine picture, including the wind turbine picture and the wind turbine mask, and use the wind turbine picture and the wind turbine mask to form an image-mask pair for training the full convolutional neural network. model, and calculate and record the value of the model loss function during the training process. Then, the trained model is used to semantically segment the wind turbine pictures obtained in the actual application scenario, and the wind turbine prediction mask is obtained, and then the defects of the wind turbine are identified. Taking defect features as input and defect type as output, a defect type description formula f(type) is established, and the defect type can be shown in Table 1. Specifically, the types of wind turbine defects include, but are not limited to, one or more of contamination, wear, cracking, delamination, cracks, and lightning strikes. Specific defect types may include the types described in Table 1.

Table 1 Description of defect types

To sum up, the method provided in the embodiment of the present application adopts a fully convolutional neural network model, and labels the defect information in the wind turbine picture through labelme for training, which can identify dirt, wear, cracking, delamination, cracks, and lightning strikes. and other defects, the defect assessment method is more intelligent and accurate.

In some examples, the above-mentioned obtaining the weighting coefficients corresponding to the above-mentioned defect type, the above-mentioned defect absolute position and the above-mentioned defect size characteristic parameter includes:

The above-mentioned acquisition of the above-mentioned defect type, the above-mentioned absolute position of the defect, and the above-mentioned characteristic parameter of the defect size are used as evaluation parameters to carry out an expert scoring operation to obtain relative importance information, wherein the above-mentioned relative importance information is the relative importance degree information between each two defect parameters ;

Build an evaluation matrix based on the above relative importance information;

Obtain the maximum characteristic root and the average random consistency index corresponding to the evaluation matrix, wherein the average random consistency index is determined according to the order of the evaluation matrix;

Calculate the random consistency index according to the above largest characteristic root and the above average random consistency index;

When the random consistency index is smaller than the preset consistency index, the weighting coefficients corresponding to the defect type, the absolute position of the defect, and the characteristic parameter of the defect size are calculated based on the evaluation matrix.

Exemplarily, analyze the influencing factors and levels of the defect risk of the wind turbine, and use the AHP to analyze the influence weights a1, a2, and a3 of the defect type, defect location, and defect size on the possibility of risk occurrence. The defect type, the absolute position of the defect and the characteristic parameters of the defect size are used as the evaluation parameters to carry out expert scoring operation to obtain relative importance information. If they are different, they will be scored in pairs, and rated according to their importance. a _ij is the comparison result of the importance of element i and element j, and the scoring standard is shown in Table 2:

factor i is better than factor j quantized value equally important 1 slightly important 3 Strong and important 5 strongly important 7 extremely important 9 The median value of two adjacent judgments 2, 4, 6, 8

Table 2 Scoring standard table

The scores of each expert are normalized, and the pairwise comparison results are formed into an evaluation matrix. The evaluation matrix has the following properties:

Refer to Table 3 for the evaluation matrix.

Table 3 Evaluation Matrix

Carry out the consistency test of the evaluation, find the maximum characteristic root λ _max of the evaluation matrix, and determine the average random consistency index RI according to the parameter n of the evaluation matrix. The specific value of RI is shown in Table 4. To find the random consistency CR, the calculation formula is:

matrix order 1 2 3 4 5 6 7 8 9 10 RI 0 0 0.58 0.90 1.12 1.24 1.32 1.41 1.45 1.49

Table 4 is the standard value of random consistency index RI

In this embodiment, the parameter defect type, defect location, and defect size number are 3, so n=3, that is, RI=0.58. After calculation, if the consistency CR is less than 0.1 (preset consistency index), the evaluation After the consistency check of the matrix is passed, the weighting coefficients of the three parameters can be calculated.

To sum up, in the method provided in the embodiment of the present application, the defect risk level is determined by comprehensively considering the defect type, defect location, and defect size through an AHP-based defect risk assessment method for wind turbines, and the expert scoring method is used to comprehensively consider every two The influence between the parameters, and the weighting coefficient is calculated based on this, and the defect risk probability calculated by this weighting coefficient can fully reflect the influence between the parameters, and can better determine the influence of defects based on defect type, defect location, and defect size. The impact of target defects on wind turbines is judged.

In some examples, the above-mentioned calculation based on the above-mentioned evaluation matrix, the above-mentioned weighting coefficient corresponding to the above-mentioned defect type, the above-mentioned absolute position of the defect and the above-mentioned characteristic parameter of the defect size, including:

The weighting coefficients corresponding to the above-mentioned defect types, the above-mentioned defect absolute positions and the above-mentioned defect size characteristic parameters are calculated according to the following formula:

为上述加权系数，W_i为上述评估矩阵中各行元素乘积的

次方，n为上述评估矩阵对应的阶次，∑W_i为所有∑W_i的和。In the formula,

is the above weighting coefficient, W _i is the product of the elements of each row in the above evaluation matrix

power, n is the order corresponding to the above evaluation matrix, ∑W _i is the sum of all ∑W _i .

次方记为W_i，则三个参数的加权系数Exemplarily, the product of the rows of the matrix

The power is recorded as W _i , then the weighting coefficient of the three parameters

then the probability of defect risk

In some examples, the above method further includes:

Defect risk levels and corresponding preset maintenance measures are determined according to the above-mentioned defect risk probability and preset maintenance strategy table.

Exemplarily, by checking the preset maintenance strategy table according to the calculated risk probability, the risk level corresponding to the authority and the corresponding maintenance measures can be determined, which is convenient for maintenance personnel to carry out maintenance processing. The specific maintenance plan can be seen in Table 5:

Table 5 Maintenance measures taken for different defect risk levels

To sum up, in the method provided in the embodiment of the present application, by querying the corresponding table of risk levels and maintenance measures corresponding to the probability of defect risk by calculating the probability of defect risk, a scientific maintenance plan for the motor unit can be formulated, which is convenient for construction personnel to evaluate and maintain. .

Referring to FIG. 2, the present invention also proposes a wind turbine defect assessment device, including:

An identification unit 21, configured to identify the detection picture of the target wind turbine to obtain defect parameters of the target defect in the target wind turbine, wherein the defect parameters include defect type, defect absolute position and defect size characteristic parameters;

an obtaining unit 22, configured to obtain the weighting coefficients corresponding to the defect type, the absolute position of the defect and the characteristic parameter of the defect size;

The calculation unit 23 is configured to calculate the defect risk probability based on the defect type, the absolute position of the defect, the characteristic parameter of the defect size and its corresponding weighting coefficient.

As shown in FIG. 3 , an embodiment of the present application further provides an electronic device 300 , including a memory 310 , a processor 320 , and a computer program 511 stored in the memory 320 and running on the processor, and the processor 320 executes the computer program 311 When implementing the steps of any one of the above-mentioned wind turbine defect assessment methods.

Since the electronic device introduced in this embodiment is the device used to implement a wind turbine defect assessment device in the embodiment of the present application, based on the method introduced in the embodiment of the present application, those skilled in the art can understand this embodiment The specific implementation of the electronic device and its various variations, so how the electronic device implements the methods in the embodiments of the present application will not be described in detail here, as long as those skilled in the art implement the methods in the embodiments of the present application. The equipment used all belong to the scope of protection of this application.

In a specific implementation process, when the computer program 311 is executed by the processor, any one of the embodiments corresponding to FIG. 1 can be implemented.

It should be noted that, in the foregoing embodiments, the description of each embodiment has its own emphasis, and for parts that are not described in detail in a certain embodiment, reference may be made to the relevant descriptions of other embodiments.

As will be appreciated by those skilled in the art, the embodiments of the present application may be provided as a method, a system, or a computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) having computer-usable program code embodied therein.

The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the present application. It will be understood that each flow and/or block in the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to the processor of a general purpose computer, special purpose computer, embedded computer or other programmable data processing device to produce a machine such that the instructions executed by the processor of the computer or other programmable data processing device produce Means implementing the functions specified in one or more of the flowcharts and/or one or more blocks of the block diagrams.

These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory result in an article of manufacture comprising instruction means, the instructions The apparatus implements the functions specified in the flow or flow of the flowcharts and/or the block or blocks of the block diagrams.

These computer program instructions can also be loaded on a computer or other programmable data processing device to cause a series of operational steps to be performed on the computer or other programmable device to produce a computer-implemented process such that The instructions provide steps for implementing the functions specified in the flow or blocks of the flowcharts and/or the block or blocks of the block diagrams.

The embodiment of the present application also provides a computer program product, the computer program product includes computer software instructions, when the computer software instructions are run on the processing device, the processing device is made to execute the wind turbine defect assessment method in the embodiment corresponding to FIG. 1 . process.

A computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the procedures or functions according to the embodiments of the present application are generated in whole or in part. The computer may be a general purpose computer, a special purpose computer, a computer network, or other programmable device. Computer instructions may be stored in or transmitted from one computer-readable storage medium to another computer-readable storage medium, for example, the computer instructions may be transmitted from a website site, computer, server, or data center over a wire (e.g. Coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (eg infrared, wireless, microwave, etc.) means to transmit to another website site, computer, server or data center. The computer-readable storage medium can be any available medium that can be stored by a computer or a data storage device such as a server, a data center, etc. that includes one or more available media integrated. Useful media may be magnetic media (eg, floppy disks, hard disks, magnetic tapes), optical media (eg, DVDs), or semiconductor media (eg, solid state disks (SSDs)), and the like.

Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the system, device and unit described above may refer to the corresponding process in the foregoing method embodiments, which will not be repeated here.

In the several embodiments provided in this application, it should be understood that the disclosed system, apparatus and method may be implemented in other manners. For example, the apparatus embodiments described above are only illustrative. For example, the division of units is only a logical function division. In actual implementation, there may be other division methods, for example, multiple units or components may be combined or integrated. to another system, or some features can be ignored, or not implemented. On the other hand, the shown or discussed mutual coupling or direct coupling or communication connection may be through some interfaces, indirect coupling or communication connection of devices or units, and may be in electrical, mechanical or other forms.

Units described as separate components may or may not be physically separated, and components shown as units may or may not be physical units, that is, may be located in one place, or may be distributed to multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution in this embodiment.

In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically alone, or two or more units may be integrated into one unit. The above-mentioned integrated units may be implemented in the form of hardware, or may be implemented in the form of software functional units.

The integrated unit, if implemented as a software functional unit and sold or used as a stand-alone product, may be stored in a computer-readable storage medium. Based on this understanding, the technical solutions of the present application can be embodied in the form of software products in essence, or the parts that contribute to the prior art, or all or part of the technical solutions, and the computer software products are stored in a storage medium , including several instructions to cause a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods in the various embodiments of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory, ROM), random access memory (Random Access Memory, RAM), magnetic disk or optical disk and other media that can store program codes .

The above embodiments are only used to illustrate the technical solutions of the present application, but not to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: The recorded technical solutions are modified, or some technical features thereof are equivalently replaced; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions in the embodiments of the present application.

Claims (10)

1. a wind turbine defect assessment method, is characterized in that, comprises: Identifying the detection picture of the target wind turbine to obtain defect parameters of the target defect in the target wind turbine, wherein the defect parameters include defect type, defect absolute position and defect size characteristic parameters; Obtain the weighting coefficients corresponding to the defect type, the absolute position of the defect and the characteristic parameter of the defect size; The defect risk probability is calculated based on the defect type, the absolute position of the defect, the characteristic parameter of the defect size and its corresponding weighting coefficient. 2. The method of claim 1, wherein the method further comprises: Obtain the drone coordinate information, shooting parameter information and wind turbine size information of the target drone, wherein the shooting parameter information includes the angle information and camera focal length information corresponding to the target drone and the target camera carried by the target drone. The target camera is a camera used to shoot the detection picture; A coordinate transformation operation is performed based on the coordinate information of the UAV, the photographing parameter information and the size information of the wind turbine to obtain the absolute position of the defect, wherein the absolute position of the defect includes the position in the length direction of the defect and the position in the width direction of the defect. 3. The method of claim 1, wherein the method further comprises: obtaining the defective pixel area of the target defect; Obtain the part length of the part corresponding to the target defect; The defect size characteristic parameter is calculated based on the part length and the defect area. 4. The method of claim 1, wherein the method further comprises: Identify the detection picture based on the target full convolutional neural network model to obtain the defect type, wherein the target full convolutional neural network model is obtained by training the training picture with the defect type marked by labelme, and the defect Types include at least one of soiling, abrasion, cracking, delamination, cracking, and lightning strikes. 5. The method according to claim 1, wherein the obtaining the weighting coefficients corresponding to the defect type, the absolute position of the defect and the characteristic parameter of the defect size comprises: The obtaining of the defect type, the absolute position of the defect, and the characteristic parameter of the defect size are used as evaluation parameters to perform expert scoring operations to obtain relative importance information, wherein the relative importance information is the difference between each two defect parameters. relative importance information; constructing an evaluation matrix based on the relative importance information; Obtain the maximum characteristic root and the average random consistency index corresponding to the evaluation matrix, wherein the average random consistency index is determined according to the order of the evaluation matrix; Calculate the random consistency index according to the largest characteristic root and the average random consistency index; In the case that the random consistency index is smaller than the preset consistency index, the weighting coefficients corresponding to the defect type, the defect absolute position and the defect size characteristic parameter are calculated based on the evaluation matrix. 6. The method according to claim 5, wherein the calculating, based on the evaluation matrix, the weighting coefficients corresponding to the defect type, the defect absolute position and the defect size characteristic parameter, comprising: Calculate the weighting coefficient corresponding to the defect type, the absolute position of the defect and the characteristic parameter of the defect size according to the following formula:

In the formula,

is the weighting coefficient, W _i is the product of the elements of each row in the evaluation matrix

power, n is the order corresponding to the evaluation matrix, ΣW _i is the sum of all ΣW _i . 7. The method of claim 1, wherein the method further comprises: Defect risk levels and corresponding preset maintenance measures are determined according to the defect risk probability and preset maintenance strategy table. 8. A wind turbine defect assessment device, characterized in that, comprising: an identification unit, configured to identify the detection picture of the target wind turbine to obtain defect parameters of the target defect in the target wind turbine, wherein the defect parameters include defect type, defect absolute position and defect size characteristic parameters; an obtaining unit, configured to obtain the weighting coefficient corresponding to the defect type, the absolute position of the defect and the characteristic parameter of the defect size; A calculation unit, configured to calculate the defect risk probability based on the defect type, the absolute position of the defect, the characteristic parameter of the defect size and its corresponding weighting coefficient. 9. An electronic device comprising: a memory, a processor and a computer program stored in the memory and running on the processor, wherein the processor is used to execute the computer program stored in the memory when Steps of implementing the method for assessing defects of a wind turbine as claimed in any one of claims 1-7. 10 . A computer-readable storage medium on which a computer program is stored, characterized in that: when the computer program is executed by a processor, the method for evaluating a defect of a wind turbine according to any one of claims 1-7 is implemented.

Images