A method and system for inspecting welds and bolts in wind turbine towers

Abstract

This invention relates to the field of defect detection technology and discloses a method and system for detecting welds and bolts in wind turbine towers. The method is executed by a data processing device within a wind turbine tower weld and bolt detection system, which also includes a wall-climbing adsorption robot communicatively connected to the data processing device. The method includes: acquiring ultrasonic images of the wind turbine tower surface; obtaining the ultrasonic images by scanning the wind turbine tower surface using the wall-climbing adsorption robot; performing anisotropic diffusion denoising processing on the ultrasonic images to obtain a smoothed ultrasonic image; and processing the smoothed ultrasonic image using a defect detection model to obtain the defect detection result. The defect detection model is a neural network model pre-trained using sample images of the wind turbine tower surface. This solution offers high accuracy and efficiency in detecting welds and bolts in wind turbine towers.

Description

Technical Field

[0001] This invention relates to the field of defect detection technology, specifically to a method and system for detecting welds and bolts in wind turbine towers. Background Technology

[0002] The wind turbine tower is the structural support system that mounts the wind turbine generator high above the ground. It bears the weight of the wind turbine generator and elevates it to a greater height. This ensures the stability and safety of the entire wind turbine system while allowing the generator to more effectively capture high-altitude winds, thereby improving power generation efficiency. Welds and bolts are crucial components of the wind turbine tower's support structure. Poor weld quality or inadequate bolt tightening can lead to loosening or deformation of the tower during operation, affecting the stability and efficiency of the entire wind turbine system. Therefore, regular inspection of the wind turbine tower's welds and bolts is necessary to identify problems promptly and ensure long-term stable operation of the wind turbine tower.

[0003] In related technologies, qualified inspectors work at height and in confined spaces to inspect welds and bolts on wind turbine towers. Due to limited space for personnel at height, the difficulty in setting up inspection instruments, and the safety hazards associated with working at height, the inspection process is challenging, costly, and cumbersome. Furthermore, the judgment of weld and bolt defects relies on the inspectors' subjective judgment, making accuracy difficult to guarantee. Therefore, there is an urgent need for a method that can automatically detect welds and bolts on wind turbine towers and automatically identify and analyze defects. Summary of the Invention

[0004] In view of this, the purpose of the present invention is to provide a method and system for inspecting welds and bolts of wind turbine towers, so as to solve the problems of high inspection difficulty, cumbersome operation and low accuracy when inspecting welds and bolts of wind turbine towers.

[0005] In a first aspect, the present invention provides a method for inspecting welds and bolts in a wind turbine tower, the method being executed by a data processing device of a wind turbine tower weld and bolt inspection system; the wind turbine tower weld and bolt inspection system further includes a wall-climbing adsorption robot; the wall-climbing adsorption robot is communicatively connected to the data processing device; the method includes:

[0006] Acquire ultrasonic images of the wind turbine tower surface; the ultrasonic images are obtained by the wall-climbing adsorption robot scanning the wind turbine tower surface;

[0007] Anisotropic diffusion denoising processing is performed on the ultrasound image to obtain a processed smooth ultrasound image.

[0008] The ultrasonically smoothed image is processed using a defect detection model to obtain defect detection results; the defect detection model is a neural network model that has been pre-trained using sample images of the wind turbine tower surface.

[0009] In one optional implementation, the anisotropic diffusion denoising process on the ultrasound image includes:

[0010] Obtain an anisotropic diffusion denoising model;

[0011] The ultrasound image is input into an anisotropic diffusion denoising model. The ultrasound image is iterated through the diffusion coefficient, gradient operator, and divergence operator of the anisotropic diffusion denoising model to obtain a processed smooth ultrasound image.

[0012] In one optional implementation, processing the ultrasonic smoothing image using a defect detection model to obtain defect detection results includes:

[0013] Based on the target step size, the ultrasound smoothed image is slid-cropped to generate sub-images of the ultrasound smoothed image.

[0014] The ultrasonic smoothing image is processed using a defect detection model to obtain the probability value of each defect category corresponding to each sub-image; wherein, each sub-image corresponds to a probability value of each defect category; the defect categories include weld incomplete fusion, weld incomplete penetration, weld crack, weld fatigue, bolt fracture, bolt loosening, and bolt preload reduction;

[0015] The average probability value of each defect category is taken using a voting method, and the defect category with the largest average value is determined as the defect detection result.

[0016] Secondly, the present invention provides a wind turbine tower weld and bolt inspection system, comprising:

[0017] A wall-climbing adsorption robot includes a walking adsorption mechanism, a drive mechanism, an ultrasonic detection transducer, and an ultrasonic signal transmission mechanism. The drive mechanism controls the walking adsorption mechanism, enabling the wall-climbing adsorption robot to move along a target route and adhere to the surface of a wind turbine tower. The ultrasonic detection transducer collects ultrasonic signals from the surface of the wind turbine tower and transmits them to the drive mechanism via the ultrasonic signal transmission mechanism. The drive mechanism also includes a signal transmitting and receiving device for transmitting ultrasonic signals to a ground control platform.

[0018] A ground control platform includes a data receiving module and a data processing device; the data receiving module is used to receive ultrasonic signals transmitted by the signal transmitting and receiving device; the data processing device includes:

[0019] The data acquisition module is used to acquire ultrasonic images of the surface of the wind turbine tower; the ultrasonic images are obtained by processing the ultrasonic signals.

[0020] The denoising module is used to perform anisotropic diffusion denoising processing on the ultrasound image to obtain a processed smooth ultrasound image.

[0021] The defect detection module is used to process the ultrasonic smoothed image using a defect detection model to obtain defect detection results; the defect detection model is a neural network model that has been pre-trained using sample images of the wind turbine tower surface.

[0022] In one alternative embodiment, the walking adsorption mechanism further includes two symmetrical track modules for moving on the surface of the wind turbine tower; the walking adsorption mechanism also includes a permanent magnet adsorption assembly; the permanent magnet adsorption assembly is placed at the center of gravity of the wall-climbing adsorption robot to provide the same driving torque for the two track modules.

[0023] In one optional embodiment, the drive mechanism further includes a controller, which is equipped with a curved surface motion control algorithm to calculate the output torque based on the tilt angle of the wind turbine tower surface, the friction force and contact friction coefficient between the track module and the wind turbine tower surface, the gravity of the wall-climbing adsorption robot, the turning radius, the motor and gear transmission ratio, and the motor and gear transmission efficiency, and to control the walking adsorption mechanism through the output torque.

[0024] In one alternative embodiment, the ultrasonic transducer is positioned at the front end of the wall-climbing adsorption robot and close to the surface of the wind turbine tower to emit ultrasonic waves onto the surface of the wind turbine tower and receive ultrasonic signals reflected from the surface of the wind turbine tower.

[0025] Thirdly, the present invention provides a computer device, comprising: a memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the computer instructions to perform the wind turbine tower weld and bolt inspection method of the first aspect or any corresponding embodiment described above.

[0026] Fourthly, the present invention provides a computer-readable storage medium storing computer instructions for causing a computer to execute the wind turbine tower weld and bolt inspection method of the first aspect or any corresponding embodiment described above.

[0027] Fifthly, the present invention provides a computer program product, including computer instructions, which are used to cause a computer to execute the wind turbine tower weld and bolt inspection method of the first aspect or any corresponding embodiment described above.

[0028] The technical solution provided by this invention may include the following beneficial effects:

[0029] The wind turbine tower weld and bolt inspection method provided by this invention is executed by the data processing equipment of the wind turbine tower weld and bolt inspection system. The wind turbine tower weld and bolt inspection system also includes a wall-climbing adsorption robot. The wall-climbing adsorption robot scans the surface of the wind turbine tower to obtain ultrasonic images of the wind turbine tower surface. Then, the data processing equipment performs anisotropic diffusion denoising processing on the ultrasonic images to obtain processed smooth ultrasonic images. The smooth ultrasonic images are then processed using a defect detection model to obtain defect detection results. This method avoids the problems of high inspection difficulty, high cost, cumbersome operation, and low accuracy caused by manual operation. The solution is flexible and has good accuracy and high efficiency when inspecting defects in wind turbine tower welds and bolts. Attached Figure Description

[0030] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0031] Figure 1 This is a flowchart illustrating the method for inspecting welds and bolts in wind turbine towers according to an embodiment of the present invention.

[0032] Figure 2 This is a flowchart illustrating another method for inspecting welds and bolts in a wind turbine tower according to an embodiment of the present invention.

[0033] Figure 3 This is a structural block diagram of a wind turbine tower weld and bolt inspection system according to an embodiment of the present invention;

[0034] Figure 4 This is a schematic diagram of the wall-climbing adsorption robot according to an embodiment of the present invention;

[0035] Figure 5 This is a schematic diagram of the hardware structure of a computer device according to an embodiment of the present invention. Detailed Implementation

[0036] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0037] In related technologies, qualified inspectors work at height and in confined spaces to inspect welds and bolts on wind turbine towers. Due to limited space for personnel at height, the difficulty in setting up inspection instruments, and the safety hazards associated with working at height, the inspection process is challenging, costly, and cumbersome. Furthermore, the judgment of weld and bolt defects relies on the inspectors' subjective judgment, making accuracy difficult to guarantee. Therefore, this invention provides a method for inspecting welds and bolts on wind turbine towers. This method uses a wall-climbing adsorption robot to scan the surface of the wind turbine tower to acquire ultrasonic images. The ultrasonic images are then processed by data processing equipment to obtain defect detection results, resulting in high accuracy and efficiency in inspecting welds and bolts on wind turbine towers.

[0038] According to an embodiment of the present invention, a method for inspecting welds and bolts in wind turbine towers is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0039] This embodiment provides a method for inspecting welds and bolts in wind turbine towers, executed by a data processing device of a wind turbine tower weld and bolt inspection system. The system also includes a wall-climbing adsorption robot, which is communicatively connected to the data processing device. The data processing device can be an industrial computer, laptop computer, desktop computer, etc. Figure 1 This is a flowchart of a method for inspecting welds and bolts in wind turbine towers according to an embodiment of the present invention, as follows: Figure 1 As shown, the process includes the following steps:

[0040] Step S101: Obtain an ultrasonic image of the wind turbine tower surface.

[0041] The ultrasonic image was obtained by scanning the surface of the wind turbine tower using a wall-climbing adsorption robot. The robot can adhere to and move on the wind turbine tower surface, emitting ultrasonic waves and receiving the reflected ultrasonic signals. Subsequently, a data processing device can receive these ultrasonic signals to obtain an ultrasonic image of the wind turbine tower surface.

[0042] Step S102: Perform anisotropic diffusion denoising on the ultrasound image to obtain a smoothed ultrasound image.

[0043] For example, firstly, the diffusion coefficient and diffusion step number of anisotropic diffusion are selected. The diffusion coefficient controls the propagation speed of information in different directions during anisotropic diffusion, affecting the denoising effect and the degree of image edge preservation. The diffusion step number is the number of times the diffusion process is applied to each pixel or each region. Next, an anisotropic diffusion algorithm is selected, such as a nonlinear diffusion algorithm or a structure tensor anisotropic diffusion algorithm. Finally, the selected anisotropic diffusion algorithm is used to denoise the ultrasound image, iteratively applied to each pixel or each region of the image until a preset convergence condition is reached.

[0044] Step S103: Process the ultrasonic smoothing image using a defect detection model to obtain the defect detection result.

[0045] The defect detection model is a neural network model pre-trained using sample images of the wind turbine tower surface. These sample images contain various defect images of welds and bolts on the wind turbine tower surface, such as weld cracks, non-compliance with specifications, and loose bolts. The defect detection model trained using sample images of the wind turbine tower surface can accurately identify various defects of the wind turbine tower welds and bolts, and obtain defect detection results.

[0046] The wind turbine tower weld and bolt inspection method provided in this embodiment is executed by the data processing equipment of the wind turbine tower weld and bolt inspection system. The wind turbine tower weld and bolt inspection system also includes a wall-climbing adsorption robot. The wall-climbing adsorption robot scans the surface of the wind turbine tower to obtain ultrasonic images of the wind turbine tower surface. Then, the data processing equipment performs anisotropic diffusion denoising processing on the ultrasonic images to obtain processed smooth ultrasonic images. The smooth ultrasonic images are then processed using a defect detection model to obtain defect detection results. This method avoids the problems of high inspection difficulty, high cost, cumbersome operation, and low accuracy caused by manual operation. The solution is flexible and has good accuracy and high efficiency in detecting defects in wind turbine tower welds and bolts.

[0047] This embodiment provides a method for inspecting welds and bolts in wind turbine towers, executed by a data processing device of a wind turbine tower weld and bolt inspection system. The system also includes a wall-climbing adsorption robot, which is communicatively connected to the data processing device. The data processing device can be an industrial computer, laptop computer, desktop computer, etc. Figure 2 This is a flowchart of a method for inspecting welds and bolts in wind turbine towers according to an embodiment of the present invention, as follows: Figure 2 As shown, the process includes the following steps:

[0048] Step S201: Obtain the defect detection model.

[0049] The defect detection model is a neural network model that has been pre-trained using sample images of the wind turbine tower surface.

[0050] Optionally, a sample dataset is formed by collecting sample images of various defects corresponding to welds and bolts on the wind turbine tower surface, such as weld incomplete fusion, weld incomplete penetration, weld cracks, weld fatigue, and bolt fracture, bolt loosening, and decreased bolt preload. Next, a defect detection model to be trained is obtained. This model can be a deep learning classification model, a convolutional neural network model, etc. To reduce the training load, a pre-trained model with image detection capabilities can also be used as the defect detection model to be trained. Finally, the sample dataset composed of collected wind turbine tower surface sample images is used to train the defect detection model. The wind turbine tower surface sample images are first preprocessed and then normalized as input data. The normalization formula is as follows:

[0051]

[0052] Where x1 represents the minimum value of the input data and x2 represents the maximum value of the input data.

[0053] The preprocessed sample dataset is then input into the defect detection model for training. The model parameters are updated using the cross-entropy cost function and stochastic gradient descent, and supervised fine-tuning is performed via backpropagation to optimize the model, ultimately yielding the defect detection model. The trained defect detection model can detect various defects corresponding to welds and bolts on the surface of wind turbine towers.

[0054] For example, deep learning features feature extraction and dimensionality reduction, enabling it to autonomously learn feature representations from sample data. For deep learning classification models, convolutional neural networks (CNNs) are particularly well-suited for image data processing due to their high invariance to data shifting, scaling, and distortion. The basic structure of a CNN includes: an input layer, convolutional layers, downsampling layers, connection layers, and an output layer. The formula for calculating the convolution of an image using a convolutional filter is as follows:

[0055]

[0056] Where f() represents the activation function, F conv2D Let represent the two-dimensional convolution formula, bj represent the bias value, ωij represent the weights between neurons, and yj represent the input of the j-th neuron.

[0057] Pooling layers are added after convolutional layers to subsample the feature maps. By merging pooling, the dimensionality of image features and the computational cost of the model are reduced. Fully connected layers in the network structure are used to integrate local information, and finally, a classifier is used for classification.

[0058] Step S202: Obtain an ultrasonic image of the wind turbine tower surface.

[0059] The ultrasonic image was obtained by scanning the surface of the wind turbine tower using a wall-climbing adsorption robot. Ultrasonic imaging mainly utilizes the intensity of echoes for imaging. Sound waves propagate at different speeds in different media. Ultrasonic waves, like ordinary sound waves, are mechanical waves. Generally, sound waves with frequencies higher than 20,000 Hz are considered ultrasonic waves. When encountering defects such as pores or cracks with diameters smaller than the wavelength, scattering occurs, which manifests as dark lines on the ultrasonic image. This allows for the detection of the state of the solid medium, and the resulting image is a cross-section parallel to the direction of sound propagation and perpendicular to the measurement surface of the tower.

[0060] Optionally, a B-type line scan can be used to measure the surface of the wind turbine tower to obtain an ultrasonic image.

[0061] Step S203: Perform anisotropic diffusion denoising processing on the ultrasound image to obtain a processed smooth ultrasound image.

[0062] Specifically, step S203 includes:

[0063] Step S2031: Obtain the anisotropic diffusion denoising model.

[0064] The main principle of anisotropic diffusion is to convolve the variance of the Gaussian kernel G with the time variable t and the noisy image, and use the image to be processed I0 as the medium to diffuse the image at a variable rate to obtain an enhanced smooth image.

[0065] Step S2032: Input the ultrasound image into the anisotropic diffusion denoising model, and iterate the ultrasound image using the diffusion coefficient, gradient operator and divergence operator of the anisotropic diffusion denoising model to obtain the processed smooth ultrasound image.

[0066] For example, the thermal diffusion equation is as follows:

[0067]

[0068] Where I(x,y,t) represents the original ultrasound image, the time variable t represents the order parameter, and the diffusion process evolves over time, i.e., the number of iterations, c(x,y,t). and div represent the diffusion coefficient, gradient operator, and divergence operator, respectively. Their magnitudes depend on the strength of the gradient, and are generally taken as I(x,y,t) = g(I(x,y,t)).

[0069] Step S204: Process the ultrasonic smoothing image using a defect detection model to obtain the defect detection result.

[0070] Specifically, step S204 includes:

[0071] Step S2041: Based on the target step size, the ultrasound smoothed image is slid-cropped to generate various sub-images of the ultrasound smoothed image.

[0072] The target step size can be selected according to actual needs, for example, it can be set to 10.

[0073] Step S2042: Process each sub-image of the ultrasonic smoothing image using the defect detection model to obtain the probability value of each defect category corresponding to each sub-image.

[0074] The defect classification includes incomplete weld fusion, incomplete weld penetration, weld cracks, weld fatigue, bolt breakage, bolt loosening, and reduced bolt preload.

[0075] For example, each sub-image of the ultrasound smoothing image is preprocessed and normalized before being input into the defect detection model for feature extraction and defect detection. Then, a Softmax classifier is used to obtain the probability value of each defect category corresponding to each sub-image, where each sub-image corresponds to a probability value of each defect category.

[0076] Step S2043: Use the voting method to take the average of the probability values ​​of each defect category, and determine the defect category with the largest average as the defect detection result.

[0077] The probability values ​​of each defect category corresponding to each sub-image are statistically analyzed using a voting method. The average probability value of each defect category is taken, and the defect category with the largest average probability value is determined as the defect detection result of the ultrasonically smoothed image. Since there may be multiple defects in the welds and bolts on the surface of the wind turbine tower, the defect category with the largest number of targets with the largest average probability value can also be used as the defect detection result of the ultrasonically smoothed image. For example, the top three defect categories with the largest average probability values ​​can be determined as the defect detection results.

[0078] The wind turbine tower weld and bolt inspection method provided in this embodiment is executed by the data processing equipment of the wind turbine tower weld and bolt inspection system. The wind turbine tower weld and bolt inspection system also includes a wall-climbing adsorption robot. The wall-climbing adsorption robot scans the surface of the wind turbine tower to obtain ultrasonic images of the wind turbine tower surface. Then, the data processing equipment performs anisotropic diffusion denoising processing on the ultrasonic images to obtain processed smooth ultrasonic images. The smooth ultrasonic images are then processed using a defect detection model to obtain defect detection results. This method avoids the problems of high inspection difficulty, high cost, cumbersome operation, and low accuracy caused by manual operation. The solution is flexible and has good accuracy and high efficiency in detecting defects in wind turbine tower welds and bolts.

[0079] This embodiment also provides a wind turbine tower weld and bolt inspection system. The data processing equipment in this system is used to implement the above embodiments and preferred embodiments, and will not be repeated hereafter. As used below, the term "module" can be a combination of software and / or hardware that performs a predetermined function.

[0080] This embodiment provides a system for inspecting welds and bolts in wind turbine towers, such as... Figure 3 As shown, it includes a wall-climbing adsorption robot and a ground control platform.

[0081] Figure 4 A schematic diagram of the wall-climbing adsorption robot according to an embodiment of the present invention is shown. The wall-climbing adsorption robot includes a walking adsorption mechanism 1, a drive mechanism 2, an ultrasonic detection transducer 4, and an ultrasonic signal transmission mechanism 5. The drive mechanism 2 controls the walking adsorption mechanism 1, enabling the wall-climbing adsorption robot to move along a target route and adhere to the surface of the wind turbine tower. The ultrasonic detection transducer 4 collects ultrasonic signals from the surface of the wind turbine tower and transmits them to the drive mechanism 2 via the ultrasonic signal transmission mechanism 5. The drive mechanism 2 also includes a signal transmitting and receiving device for transmitting the ultrasonic signals to a ground control platform.

[0082] The ground control platform includes a data receiving module and a data processing device. The data receiving module receives ultrasonic signals transmitted by the signal transmitting and receiving device. The data processing device includes a data acquisition module, a denoising module, and a defect detection module. The data acquisition module acquires ultrasonic images of the wind turbine tower surface. These ultrasonic images are obtained through ultrasonic signal processing; for example, the data acquisition module performs ultrasonic imaging processing on the ultrasonic signals to obtain the ultrasonic image. The denoising module performs anisotropic diffusion denoising processing on the ultrasonic image to obtain a processed, smoothed ultrasonic image. The defect detection module processes the smoothed ultrasonic image using a defect detection model to obtain defect detection results. The defect detection model is a neural network model pre-trained using sample images of the wind turbine tower surface.

[0083] In one optional implementation, the denoising module is further configured to obtain an anisotropic diffusion denoising model, input the ultrasound image into the anisotropic diffusion denoising model, and iterate the ultrasound image using the diffusion coefficient, gradient operator, and divergence operator of the anisotropic diffusion denoising model to obtain a processed smooth ultrasound image.

[0084] In one optional implementation, the defect detection module is further configured to perform sliding cropping on the ultrasonically smoothed image based on a target step size to generate sub-images of the ultrasonically smoothed image, process each sub-image of the ultrasonically smoothed image using a defect detection model, and obtain the probability value of each defect category corresponding to each sub-image; wherein, each sub-image corresponds to a probability value of each defect category; the defect categories include weld incomplete fusion, weld incomplete penetration, weld crack, weld fatigue, bolt fracture, bolt loosening, and bolt preload reduction, and the average probability value of each defect category is taken using a voting method, and the defect category with the largest average value is determined as the defect detection result.

[0085] In one optional embodiment, the walking adsorption mechanism further includes two symmetrical track modules for moving on the surface of the wind turbine tower. The walking adsorption mechanism 1 also includes a powerful permanent magnet adsorption component, which is a crucial functional part of the wall-climbing robot. Especially since the robot needs to operate at heights of tens of meters, it must possess strong adsorption force to cope with the wall adhesion and load-bearing capacity required for high-altitude operations. This permanent magnet adsorption component is placed at the center of gravity of the wall-climbing adsorption robot to provide the same driving torque to the two track modules, ensuring a uniform distribution of adsorption force at the center of the robot. This allows it to adhere to magnetically conductive walls such as wind turbine towers and move across the tower surface via the track modules, resulting in stable movement and flexible steering. Optionally, the permanent magnet adsorption component uses neodymium iron boron magnets, a material with high powder, high pressure, very high density, large magnetic capacity, and strong adsorption force. It is heat-resistant, hard, and can lift objects hundreds of times its own weight, 30 to 50 times stronger than ordinary magnets of the same volume.

[0086] In one optional embodiment, the drive mechanism 2 is housed within the motor compartment of the track module in the walking adsorption structure 1. It controls the movement of the walking adsorption mechanism 1 on the magnetically conductive curved surface and receives signals from the ultrasonic transducer 4, which are then wirelessly transmitted to the ground control platform. The drive mechanism 2 also includes a controller. After the signal transmitting and receiving device receives the movement signal wirelessly transmitted from the ground control platform, the controller controls the direction and distance of movement of the wall-climbing adsorption robot based on the movement signal. Specifically, the controller is equipped with a curved surface motion control algorithm. The controller can control the drive element motor in the drive mechanism 2 according to the algorithm to ensure stable movement and precise positioning of the robot on the curved surface. Optionally, the controller calculates the output torque based on the tilt angle of the wind turbine tower surface, the friction and contact friction coefficient between the track module and the wind turbine tower surface, the gravity of the wall-climbing adsorption robot, the turning radius, the motor and gear transmission ratio, and the motor and gear transmission efficiency, and controls the walking adsorption mechanism through the output torque. For example, the output torque M of the drive element motor... T for:

[0087]

[0088] Where μ is the coefficient of friction between the track module and the surface of the wind turbine tower, F0 is the frictional force between the track module and the surface of the wind turbine tower, G is the gravity of the wall-climbing adsorption robot, R is the turning radius of the wall-climbing adsorption robot, β is the tilt angle of the wind turbine tower surface, i is the transmission ratio from the motor to the planetary gears of the wall-climbing adsorption robot (motor and gear transmission ratio), and η is the total efficiency of the wall-climbing adsorption robot from motor transmission to the final output of the motor to the drive wheel (motor and gear transmission efficiency).

[0089] Optionally, the wireless communication between the signal transmitting and receiving device of the wall-climbing adsorption robot and the data receiving module of the ground control platform adopts millimeter-wave wireless communication technology, using a frequency range between 30GHz and 300GHz and a wavelength of approximately 1mm to 10mm. Compared with existing wireless communication technologies such as Wi-Fi, millimeter-wave wireless communication technology has a larger bandwidth and a higher data rate, enabling stable transmission of control signals and ultrasonic detection signals.

[0090] In one alternative implementation, the ultrasonic transducer is positioned at the front end of the wall-climbing adsorption robot and close to the surface of the wind turbine tower to emit ultrasonic waves onto the surface of the wind turbine tower and receive ultrasonic signals reflected from the surface of the wind turbine tower.

[0091] In one alternative embodiment, the wall-climbing adsorption robot further includes a power supply mechanism 3 for providing a stable DC power supply to the walking adsorption mechanism 1, the drive mechanism 2, the ultrasonic detection transducer 4, and the ultrasonic signal transmission mechanism 5.

[0092] Further functional descriptions of the above modules and units are the same as those in the corresponding embodiments described above, and will not be repeated here.

[0093] In this embodiment, the data processing equipment in the wind turbine tower weld and bolt inspection system is presented in the form of a functional unit. Here, a unit refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and memory that execute one or more software or fixed programs, and / or other devices that can provide the above functions.

[0094] This invention also provides a computer device having the data processing equipment in the above-mentioned wind turbine tower weld and bolt detection system.

[0095] Please see Figure 5 , Figure 5 This is a schematic diagram of the structure of a computer device provided in an optional embodiment of the present invention, such as... Figure 5As shown, the computer device includes one or more processors 10, memory 20, and interfaces for connecting the components, including high-speed interfaces and low-speed interfaces. The components communicate with each other via different buses and can be mounted on a common motherboard or otherwise installed as needed. The processors can process instructions executed within the computer device, including instructions stored in or on memory to display graphical information of a GUI on external input / output devices (such as display devices coupled to the interfaces). In some alternative implementations, multiple processors and / or multiple buses can be used with multiple memories and multiple memory modules, if desired. Similarly, multiple computer devices can be connected, each providing some of the necessary operations (e.g., as a server array, a group of blade servers, or a multiprocessor system). Figure 5 Take a processor 10 as an example.

[0096] Processor 10 may be a central processing unit, a network processor, or a combination thereof. Processor 10 may further include a hardware chip. The hardware chip may be an application-specific integrated circuit (ASIC), a programmable logic device (PLD), or a combination thereof. The programmable logic device may be a complex programmable logic device (CAMP), a field-programmable gate array (FPGA), a general-purpose array logic (GPA), or any combination thereof.

[0097] The memory 20 stores instructions executable by at least one processor 10 to cause the at least one processor 10 to perform the method shown in the above embodiments.

[0098] The memory 20 may include a program storage area and a data storage area. The program storage area may store the operating system and applications required for at least one function; the data storage area may store data created based on the use of the computer device. Furthermore, the memory 20 may include high-speed random access memory and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some alternative embodiments, the memory 20 may optionally include memory remotely located relative to the processor 10, and these remote memories may be connected to the computer device via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

[0099] The memory 20 may include volatile memory, such as random access memory; the memory may also include non-volatile memory, such as flash memory, hard disk or solid-state drive; the memory 20 may also include a combination of the above types of memory.

[0100] The computer device also includes an input device 30 and an output device 40. The processor 10, memory 20, input device 30, and output device 40 can be connected via a bus or other means. Figure 5 Taking the example of a connection between China and Israel via a bus.

[0101] Input device 30 can receive input numerical or character information, and generate key signal inputs related to user settings and function control of the computer device, such as a touchscreen, keypad, mouse, trackpad, touchpad, joystick, one or more mouse buttons, trackball, joystick, etc. Output device 40 may include display devices, auxiliary lighting devices (e.g., LEDs), and haptic feedback devices (e.g., vibration motors). The aforementioned display devices include, but are not limited to, liquid crystal displays, light-emitting diodes, displays, and plasma displays. In some alternative embodiments, the display device may be a touchscreen.

[0102] This invention also provides a computer-readable storage medium. The methods described above according to embodiments of the invention can be implemented in hardware or firmware, or implemented as computer code that can be recorded on a storage medium, or implemented as computer code downloaded via a network and originally stored on a remote storage medium or a non-transitory machine-readable storage medium and then stored on a local storage medium. Thus, the methods described herein can be processed by software stored on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. The storage medium can be a magnetic disk, optical disk, read-only memory, random access memory, flash memory, hard disk, or solid-state drive, etc.; further, the storage medium can also include combinations of the above types of memory. It is understood that computers, processors, microprocessor controllers, or programmable hardware include storage components capable of storing or receiving software or computer code, which, when accessed and executed by the computer, processor, or hardware, implements the methods shown in the above embodiments.

[0103] A portion of this invention can be applied as a computer program product, such as computer program instructions, which, when executed by a computer, can invoke or provide the methods and / or technical solutions according to the invention through the operation of the computer. Those skilled in the art will understand that the forms in which computer program instructions exist in a computer-readable medium include, but are not limited to, source files, executable files, installation package files, etc. Correspondingly, the ways in which computer program instructions are executed by a computer include, but are not limited to: the computer directly executing the instructions, or the computer compiling the instructions and then executing the corresponding compiled program, or the computer reading and executing the instructions, or the computer reading and installing the instructions and then executing the corresponding installed program. Here, the computer-readable medium can be any available computer-readable storage medium or communication medium accessible to a computer.

[0104] Although embodiments of the present invention have been described in conjunction with the accompanying drawings, those skilled in the art can make various modifications and variations without departing from the spirit and scope of the present invention, and all such modifications and variations fall within the protection scope of the present invention.

Claims

1. A method of wind turbine tower weld and bolt inspection, the method comprising: The method is executed by a data processing device of a wind turbine tower weld and bolt detection system; the wind turbine tower weld and bolt detection system further comprises a wall-climbing adsorption robot; the wall-climbing adsorption robot is in communication connection with the data processing device; the method comprises: acquiring an ultrasonic image of a surface of a wind turbine tower; the ultrasonic image is obtained by scanning the surface of the wind turbine tower by the wall-climbing adsorption robot; performing anisotropic diffusion denoising processing on the ultrasonic image to obtain a processed ultrasonic smooth image; processing the ultrasonic smooth image by using a defect detection model to obtain a defect detection result; the defect detection model is a neural network model trained in advance by using sample images of the surface of the wind turbine tower; the anisotropic diffusion denoising processing on the ultrasonic image comprises: acquiring an anisotropic diffusion denoising model; inputting the ultrasonic image into the anisotropic diffusion denoising model, and performing iteration on the ultrasonic image by using a diffusion coefficient, a gradient operator and a divergence operator of the anisotropic diffusion denoising model to obtain the processed ultrasonic smooth image; the processing of the ultrasonic smooth image by using the defect detection model to obtain the defect detection result comprises: performing sliding cropping on the ultrasonic smooth image based on a target step length to generate each sub-image of the ultrasonic smooth image; processing each sub-image of the ultrasonic smooth image by using the defect detection model to respectively obtain probability values of each defect classification corresponding to each sub-image; each sub-image corresponds to probability values of each defect classification; the defect classification comprises incomplete fusion of a weld, incomplete penetration of a weld, weld crack, weld fatigue, bolt fracture, bolt loosening and bolt pre-tightening force drop; taking the mean value of the probability values of each defect classification by using a voting method, and determining the defect classification with the maximum mean value as the defect detection result.

2. A wind turbine tower weld and bolt inspection system, characterized by, The system is used for executing the wind turbine tower weld and bolt detection method of claim 1; the system comprises: a wall-climbing adsorption robot comprising a walking adsorption mechanism, a driving mechanism, an ultrasonic detection transducer and an ultrasonic signal transmission mechanism; the driving mechanism is used for controlling the walking adsorption mechanism so that the wall-climbing adsorption robot moves on the surface of the wind turbine tower according to a target route; the ultrasonic detection transducer is used for collecting ultrasonic signals of the surface of the wind turbine tower and transmitting the ultrasonic signals to the driving mechanism through the ultrasonic signal transmission mechanism; the driving mechanism further comprises a signal transmitting and receiving device used for transmitting the ultrasonic signals to a ground control platform; a ground control platform comprising a data receiving module and a data processing device; the data receiving module is used for receiving the ultrasonic signals transmitted by the signal transmitting and receiving device; the data processing device comprises: a data acquisition module used for acquiring an ultrasonic image of the surface of the wind turbine tower; the ultrasonic image is obtained by processing the ultrasonic signals; a denoising module used for performing anisotropic diffusion denoising processing on the ultrasonic image to obtain a processed ultrasonic smooth image; a defect detection module used for processing the ultrasonic smooth image by using a defect detection model to obtain a defect detection result; the defect detection model is a neural network model trained in advance by using sample images of the surface of the wind turbine tower.

3. The system of claim 2, wherein, The walking adsorption mechanism further comprises two symmetrical track modules for moving on the surface of the fan tower drum; the walking adsorption mechanism further comprises a permanent magnet adsorption assembly; the permanent magnet adsorption assembly is placed at the center of gravity of the wall-climbing adsorption robot to provide the same driving torque for the two track modules.

4. The system of claim 3, wherein, The driving mechanism further comprises a controller, and a curved surface motion control algorithm is arranged in the controller, which is used to calculate an output torque according to the inclination angle of the surface of the wind power tower drum, the friction and the contact friction coefficient between the track module and the surface of the fan tower drum, the gravity of the wall-climbing adsorption robot, the turning radius, the gear transmission ratio and the gear transmission efficiency of the motor, and control the walking adsorption mechanism through the output torque.

5. The system of any one of claims 2 to 4, wherein, The ultrasonic detection transducer is arranged at the front end of the wall-climbing adsorption robot and close to the surface of the fan tower drum, so as to emit ultrasonic waves to the surface of the fan tower drum and receive the ultrasonic signals reflected by the surface of the fan tower drum.

6. A computer device, comprising: The wind turbine tower welding seam and bolt detection method comprises the following steps: The memory and the processor are connected in communication with each other, the memory stores computer instructions, and the processor executes the computer instructions to perform the wind turbine tower welding seam and bolt detection method.

7. A computer readable storage medium characterized in that, The computer readable storage medium stores computer instructions for enabling a computer to execute the wind turbine tower welding seam and bolt detection method.

8. A computer program product, characterised in that, The computer instructions are used for enabling a computer to execute the wind turbine tower welding seam and bolt detection method.

Images