Ground wire winding and reeling control method and system

Abstract

The present disclosure relates to the field of electric power technology, and discloses a ground wire winding and take-up control method and system. The specific scheme is: using a crack extension prediction model, processing the bearing operation data and surface crack information, and predicting the crack extension information of the bearing within a preset time in the future; when the crack extension information does not meet the preset crack extension requirements, based on the key take-up parameters of the bearing and the crack extension information, predict the degree of deterioration of the bearing take-up accuracy due to the extension crack of the bearing within the future time; based on the degree of deterioration, adjust the operating conditions of the bearing to adjust the take-up strategy of the ground wire, and control the crack extension information and take-up key parameters of the bearing.

Description

Technical Field

[0001] The present disclosure relates to the field of electric power technology, and in particular to a ground wire winding and reeling control method, system, electronic device and storage medium. Background Art

[0002] In high-speed precision wire-winding equipment, winding bearings are one of the key components. Long-term high-speed operation will cause micro cracks on the bearing surface. The generation and expansion of cracks will affect the rigidity and concentricity of the bearing, and thus affect the accuracy and stability of wire-winding.

[0003] As the equipment is used for a longer time, the micro cracks on the bearing surface will gradually increase and expand, the rigidity of the bearing will gradually decrease, and the gap between the inner and outer rings of the bearing will gradually increase. The decrease in bearing rigidity will cause the take-up shaft to produce greater radial vibration when rotating at high speed, reducing the stability of the take-up tension. The increase in bearing clearance will reduce the rotation accuracy of the take-up shaft, the consistency of material arrangement will deteriorate during the take-up process, and the take-up effect will deteriorate. In addition, the expansion speed of the bearing crack is also related to the working conditions of the equipment. The higher the take-up speed and the greater the take-up tension, the faster the cracks on the bearing surface will expand, and the faster the bearing rigidity and accuracy will decrease.

[0004] Therefore, it is necessary to study the formation mechanism and expansion law of cracks on the surface of winding bearings, establish a quantitative relationship between bearing cracks and wire-taking accuracy, guide the maintenance and update of precision wire-taking equipment, and ensure the long-term and stable operation of wire-taking equipment. Summary of the invention

[0005] The present disclosure provides a ground wire winding and wire retraction control method, system, electronic device and storage medium, which can solve at least one of the above problems.

[0006] The present disclosure provides a ground wire winding and reeling control method, comprising:

[0007] Determining surface crack information of the bearing based on a surface image of the bearing for winding the ground wire;

[0008] Monitoring the operation process of the bearing to obtain bearing operation data of the bearing;

[0009] Using a crack propagation prediction model, the bearing operation data and the surface crack information are processed to predict the crack propagation information of the bearing within a preset time in the future;

[0010] In the case where the crack propagation information does not meet the preset crack propagation requirements, based on the key wire-receiving parameters of the bearing and the crack propagation information, predicting the degree of degradation of the wire-receiving accuracy of the bearing due to the propagation crack of the bearing in the future time;

[0011] Based on the degree of deterioration, the operating condition of the bearing is adjusted to adjust the wire-receiving strategy of the ground wire and control the crack propagation information and key wire-receiving parameters of the bearing.

[0012] According to another aspect of the present disclosure, a ground wire winding and reeling control system is provided, comprising:

[0013] A first data determination module, configured to determine surface crack information of the bearing based on a surface image of the bearing for winding and collecting the ground wire;

[0014] A second data determination module, used for monitoring the operation process of the bearing to obtain bearing operation data of the bearing;

[0015] An expansion crack prediction module is used to process the bearing operation data and the surface crack information using a crack expansion prediction model to predict the crack expansion information of the bearing within a preset time in the future;

[0016] An accuracy degradation prediction module, used for predicting the degree of degradation of the bearing's take-up accuracy due to the propagation crack of the bearing within the future time based on the key take-up parameters of the bearing and the crack propagation information when the crack propagation information does not meet the preset crack propagation requirements;

[0017] An operating condition adjustment module is used to adjust the operating condition of the bearing based on the degree of deterioration, so as to adjust the wire-receiving strategy of the ground wire and control the crack propagation information and key wire-receiving parameters of the bearing.

[0018] According to another aspect of the present disclosure, there is provided an electronic device, comprising:

[0019] at least one processor; and

[0020] a memory communicatively connected to the at least one processor; wherein,

[0021] The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute any ground wire winding and reeling control method in the embodiments of the present disclosure.

[0022] According to another aspect of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are used to enable the computer to execute any ground wire winding and retracting control method in the embodiments of the present disclosure.

[0023] By adopting the technical solution of the present invention, the surface crack information of the bearing is determined based on the surface image of the bearing that is wound around the ground wire; the operation process of the bearing is monitored to obtain the bearing operation data of the bearing; the bearing operation data and the surface crack information are processed by using a crack extension prediction model to predict the crack extension information of the bearing within a preset time in the future. In this way, the crack extension information of the bearing can be accurately predicted. If the crack extension information does not meet the preset crack extension requirements, the degree of degradation of the bearing's winding accuracy due to the extended crack of the bearing within the future time is predicted based on the key winding parameters of the bearing and the crack extension information; thus, based on the degree of degradation, the operating condition of the bearing is adjusted to adjust the winding strategy of the ground wire and control the crack extension information and the key winding parameters of the bearing. Therefore, by adopting the technical solution of the present invention, the crack extension of the bearing can be controlled. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] Figure 1 is a flow chart of a ground wire winding and reeling control method according to an embodiment of the present disclosure;

[0025] Figure 2 is a structural block diagram of a ground wire winding and take-up control system according to an embodiment of the present disclosure;

[0026] Figure 3 is a block diagram of an electronic device for implementing an embodiment of the present disclosure. DETAILED DESCRIPTION

[0027] The following is a description of exemplary embodiments of the present disclosure in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0028] Figure 1 4 is a flow chart of a ground wire winding and retracting control method according to an embodiment of the present disclosure.

[0029] like Figure 1 As shown, the ground wire winding and reeling control method may include:

[0030] S110, determining surface crack information of the bearing based on a surface image of the bearing on which the ground wire is wound;

[0031] S1120, monitoring the operation process of the bearing to obtain bearing operation data of the bearing;

[0032] S130, using a crack propagation prediction model to process the bearing operation data and surface crack information, and predict the crack propagation information of the bearing within a preset time in the future;

[0033] S140, when the crack propagation information does not meet the preset crack propagation requirement, based on the key wire-taking parameters of the bearing and the crack propagation information, predicting the degree of degradation of the wire-taking accuracy of the bearing due to the propagation crack of the bearing in the future;

[0034] S150, based on the degree of deterioration, adjusts the operating conditions of the bearing to adjust the take-up strategy of the ground wire and controls the crack propagation information and key take-up parameters of the bearing.

[0035] For example, a scanning electron microscope can be used to scan the bearing surface at a high magnification to obtain a surface image. For a scanning electron microscope, the optimal scanning parameters are determined by the pre-calibrated correspondence between the image resolution and the scanning magnification. A scanning electron microscope with a resolution of 0.1 nm is used to scan the bearing surface at a high magnification of 20,000 times to obtain a surface morphology image of 2048x2048 pixels. Through the pre-calibrated correspondence, the optimal scanning parameters are determined to be an acceleration voltage of 15 kV and a working distance of 10 mm.

[0036] For example, after obtaining the surface image, the image may be preprocessed, for example, by removing noise, enhancing image contrast, etc.

[0037] Exemplarily, the surface crack information may include crack length, width, depth, density, etc., and may also include crack distribution.

[0038] Exemplarily, for the acquired original image, Gaussian filtering is used for denoising and histogram equalization is applied to enhance the contrast to obtain a clear surface microscopic morphology image. The image resolution threshold is set according to the crack characteristics to ensure that the crack edge is clearly identifiable. Crack recognition is performed on the processed surface microscopic morphology image, and the linear features in the image are extracted using the Canny edge detection algorithm. The aspect ratio threshold of the linear feature is set to screen out microscopic cracks, and the open operation is used to remove noise points, and the closed operation is used to connect the fractures to obtain a complete crack outline. The identified crack outline is refined and the crack skeleton line is extracted. The crack skeleton line is measured in size, and the length and width parameters of each crack are calculated. If the crack length is less than the preset minimum length threshold, it is determined to be noise and removed. The crack depth is estimated by the grayscale gradient and shadow characteristics of the crack edge. The effective cracks are numbered and their position coordinates and size parameters are recorded. The three-dimensional topography data of typical cracks is obtained using an atomic force microscope to calibrate the depth estimation result. Statistically analyze the spatial distribution characteristics of cracks, calculate the number of cracks per unit area to obtain the crack density. Draw the frequency distribution histogram of crack length, width, and depth. Use the K-means clustering algorithm to group the cracks, set the number of clusters to 3-5, and evaluate the optimal number of clusters by the silhouette coefficient. According to the clustering results, determine the spatial distribution mode of the cracks, such as random distribution, linear distribution, or clustered distribution.

[0039] Exemplarily, the bearing operation data of the bearing may include service load, rotation speed, temperature, etc. For example, the load, rotation speed, and temperature data of the bearing may be collected respectively by strain gauges, rotation speed sensors, and thermocouples.

[0040] Exemplarily, the crack growth prediction model may be a pre-trained model.

[0041] Exemplarily, the model can adopt a long short-term memory network structure, including two LSTM layers, each with 64 neurons, and combine with an attention mechanism to achieve online prediction of micro crack growth rate.

[0042] Exemplarily, the future time may be the next 12 hours or 24 hours.

[0043] Exemplarily, the prediction result of the crack growth prediction model may include crack growth information and its confidence level.

[0044] Exemplarily, the crack extension information may include crack extension speed, average crack length, average crack width, etc.

[0045] For example, the crack extension requirement may be that the crack extension speed is within a preset extension speed range. Alternatively, the mean value of the crack length is within a preset length threshold range. Alternatively, the mean value of the crack width is within a preset width threshold range.

[0046] For example, the key parameters of the bearing for taking up the line may include the taking-up tension and the taking-up angle, etc.

[0047] For example, a mapping model between the wire-winding accuracy and the micro-crack parameters can be pre-established through a machine learning algorithm, and then the wire-winding accuracy of the bearing in the future can be predicted through the model, thereby evaluating the degree of degradation of this accuracy.

[0048] Exemplarily, the model may also be used to directly predict the degree of degradation of accuracy.

[0049] For example, a mapping model between the degree of degradation and the operating condition of the bearing can be established in advance. The model is used to determine the operating condition corresponding to a certain degree of degradation, and then the operating condition is used to control the operation of the bearing to adjust the ground wire take-up strategy and control the crack extension information and key take-up parameters of the bearing.

[0050] According to the above-mentioned embodiment, the surface crack information of the bearing is determined based on the surface image of the bearing wound with respect to the grounding wire; the operation process of the bearing is monitored to obtain the bearing operation data of the bearing; the crack extension prediction model is used to process the bearing operation data and the surface crack information, and the crack extension information of the bearing within a preset time in the future is predicted. In this way, the crack extension information of the bearing can be accurately predicted. If the crack extension information does not meet the preset crack extension requirements, the degree of degradation of the bearing's winding accuracy due to the extended crack in the future time is predicted based on the key winding parameters of the bearing and the crack extension information. In this way, the degree of degradation of the winding accuracy can be evaluated. Subsequently, based on the degree of degradation, the operating conditions of the bearing can be accurately adjusted to adjust the winding strategy of the grounding wire and control the crack extension information and the key winding parameters of the bearing. Therefore, by adopting the technical solution disclosed in the present invention, the crack extension of the bearing can be accurately controlled to avoid the crack extending too fast and affecting the working efficiency of the bearing.

[0051] In one embodiment, based on the surface image of the bearing for winding the ground wire, the surface crack information of the bearing is determined, including: performing edge calculation on each surface image in the surface image sequence of the bearing to obtain edge features of each surface image; based on the edge features of each surface image, determining the target surface image in the surface image sequence; based on the cracks in the target surface image, determining the surface crack information of the bearing, wherein the surface crack information includes crack size, crack number and crack spatial distribution.

[0052] Exemplarily, before edge calculation is performed on the surface image, the surface image sequence of the bearing may be preprocessed. The preprocessing may include image registration of consecutive image frames, enhancing the contrast value of each image frame, and removing noise from each image frame.

[0053] For example, the image registration parameters between consecutive image frames are determined by a phase correlation method, and the image sequence is registered using the parameters to ensure the spatial consistency of the image sequence.

[0054] Exemplarily, an adaptive histogram may be used to equalize an image, thereby enhancing a local contrast value of the image.

[0055] Exemplarily, median filtering is performed on the image to remove noise in the image.

[0056] Exemplarily, the Canny edge detection operator may be used to perform edge calculation on each surface image in the surface image sequence of the bearing to obtain edge features of each surface image.

[0057] For example, an edge feature threshold may be set to determine an image with a strong edge point in the surface image sequence, and the image with the strong edge point may be used as the target image.

[0058] For example, for the target image, the Zhang-Suen thinning algorithm can be applied to extract the crack skeleton to obtain a complete crack outline with a single pixel width. For the crack skeleton, the geometric characteristic parameters such as the length, width, and direction of the crack are calculated to construct a crack feature vector.

[0059] For example, for the target image, the processed image is analyzed for crack identification and segmentation through connected domain analysis, and the geometric features such as area, perimeter, and major axis length of each connected domain are calculated. The candidate cracks are screened using a support vector machine classifier, and the input features include crack length-to-width ratio, curvature, directional consistency, etc. According to the classification results, the area that meets the crack characteristics is extracted, and finally the crack data including parameters such as crack size, number, and spatial distribution are obtained.

[0060] According to the above-mentioned embodiment, the edge features of each surface image in the surface image sequence of the bearing are utilized; based on the edge features of each surface image, the target surface image is determined in the surface image sequence, so that the surface crack information of the bearing can be accurately determined based on the cracks in the target surface image.

[0061] In one embodiment, the above method also includes: obtaining a training sample set, wherein each training sample in the training sample set includes historical bearing operation data and historical surface crack information of the bearing sample at a first historical time, and historical crack extension information at a second historical time, and the first historical time is earlier than the second historical time; for any training sample, the following operations are performed: inputting the historical bearing operation data and historical surface crack information in the training sample into a crack extension prediction model to obtain predicted crack extension information within the second historical time output by the crack extension prediction model; and updating the model parameters of the crack extension prediction model based on the historical crack extension information and predicted crack extension information within the second historical time.

[0062] Exemplarily, the bearing sample may be any bearing used for winding a ground wire.

[0063] Exemplarily, the first historical time may be adjacent to the second historical time.

[0064] Exemplarily, the historical bearing operation data, historical surface crack information, historical crack extension information, and predicted crack extension information may all refer to the above data acquisition process, which will not be described in detail here.

[0065] Exemplarily, the crack growth prediction model may adopt a residual network.

[0066] Exemplarily, the predicted crack extension information may include a crack extension rate prediction value. By integrating the crack extension rate within a given time, the crack extension amount within the given time may be obtained.

[0067] Exemplarily, the service load, rotation speed, temperature and crack size parameters obtained are input into the trained residual network model to obtain the corresponding crack growth rate prediction value.

[0068] According to the above implementation, a crack propagation prediction model can be trained.

[0069] In one embodiment, based on the key parameters of the bearing's winding, and the crack propagation information, the degree of degradation of the bearing's winding accuracy due to the propagation crack of the bearing in the future is predicted, including: performing time domain analysis on the winding tension and winding angle that change with time in the key parameters of the bearing's winding, to obtain a time domain spectrum; constructing a first eigenvector based on each feature in the time domain spectrum; selecting at least one target feature in the first eigenvector based on the mutual information value between each feature in the first eigenvector and the bearing's winding accuracy; performing data fusion based on the at least one target feature and the crack propagation information to obtain an input feature matrix; processing the input feature matrix based on a long short-term memory network to obtain the degree of degradation of the bearing's winding accuracy due to the propagation crack of the bearing in the future.

[0070] For example, before the time domain analysis, the time series data of the take-up tension and the take-up angle may be subjected to wavelet denoising and secondary Kalman filtering to obtain denoised time series data.

[0071] For example, the denoising effect is evaluated by calculating the degree of improvement in the signal-to-noise ratio, which is required to be no less than 6 dB. The denoised signal is subjected to time-frequency analysis using wavelet packet transform, the best basis function is selected, the decomposition layer number is 5, and the time domain spectrum is calculated.

[0072] Exemplarily, time-frequency domain indicators such as energy entropy, frequency center, spectrum peak, bandwidth, etc. are extracted from the time-domain spectrum to construct a first eigenvector.

[0073] Exemplarily, feature selection is performed on the extracted time-frequency domain indicators based on the mutual information criterion, the mutual information value between each feature and the line collection accuracy is calculated, and the first N features with the highest mutual information values ​​are selected, where N is a positive integer, such as 5 or 10.

[0074] Exemplarily, the filtered features are fused with the predicted crack extension information, including the mean crack length, the mean crack width and the mean crack number, to construct an input feature matrix.

[0075] Exemplarily, the long short-term memory network may be a pre-trained network. The network may represent the mapping relationship between the wire collection accuracy and the key parameters of the wire collection and the crack extension information. For example, the network may include an LSTM layer, each layer having 64 neurons.

[0076] For example, after the line-reeling accuracy is predicted, the predicted line-reeling accuracy is compared with a preset threshold value, and the degree of degradation of the predicted line-reeling accuracy can be evaluated.

[0077] According to the above implementation method, the degree of deterioration of the wire-taking accuracy of the bearing due to the extended crack of the bearing in the future is accurately evaluated.

[0078] In one embodiment, the operating condition of the bearing is adjusted based on the degree of degradation, including: when the degree of degradation of the wire-receiving accuracy of the bearing is greater than a preset degradation degree threshold, an objective function is constructed with the operating condition of the bearing as an independent variable, and the wire-receiving accuracy and crack propagation rate of the bearing as dependent variables; based on a particle swarm optimization algorithm, a minimum value of the objective function is solved to obtain a target operating condition of the bearing; and based on the target operating condition of the bearing, the operation of the bearing is controlled.

[0079] For example, the operating conditions of the bearing may include bearing speed, load, lubricant supply, etc.

[0080] For example, a single objective function is constructed with the weighted sum of the bearing's winding accuracy and crack growth rate as the dependent variable. Alternatively, a multi-objective function is constructed with the bearing's winding accuracy and crack growth rate as the dependent variables.

[0081] Exemplarily, each operating condition of the bearing is taken as an individual to construct a population.

[0082] For example, at each iteration of the population, the objective function is used to calculate the fitness of each individual in the population, and if the fitness does not meet the requirements, the population is updated. Subsequently, the updated population is used to enter the next iteration process.

[0083] Exemplarily, the number of individuals in the particle swarm may be 50, and the number of iterations may be 100.

[0084] According to the above-mentioned embodiment, the working condition of the bearing is optimized with the goal of minimizing the wire taking-up accuracy and crack growth rate of the bearing, thereby minimizing the wire taking-up accuracy and crack growth rate of the bearing.

[0085] Figure 2 It is a structural block diagram of a ground wire winding and take-up control system according to an embodiment of the present disclosure.

[0086] like Figure 2 As shown, the ground wire winding and take-up control system may include:

[0087] A first data determination module 210 is used to determine surface crack information of the bearing based on a surface image of the bearing for winding the ground wire;

[0088] A second data determination module 220, configured to monitor the operation process of the bearing and obtain bearing operation data of the bearing;

[0089] The crack extension prediction module 230 is used to process the bearing operation data and the surface crack information using a crack extension prediction model to predict the crack extension information of the bearing within a preset time in the future;

[0090] The precision degradation prediction module 240 is used to predict the degree of degradation of the bearing's take-up precision due to the propagation crack of the bearing in the future time based on the key take-up parameters of the bearing and the crack propagation information when the crack propagation information does not meet the preset crack propagation requirements;

[0091] The operating condition adjustment module 250 is used to adjust the operating condition of the bearing based on the degree of degradation, so as to adjust the wire-retrieving strategy of the ground wire and control the crack propagation information and key wire-retrieving parameters of the bearing.

[0092] In one implementation, the first data determination module 210 includes:

[0093] An edge computing unit 211 is used to perform edge computing on each surface image in the surface image sequence of the bearing to obtain edge features of each surface image;

[0094] A target image determining unit 212, configured to determine a target surface image in the surface image sequence based on edge features of each of the surface images;

[0095] The crack information determination unit 213 is used to determine the surface crack information of the bearing based on the cracks in the target surface image, wherein the surface crack information includes crack size, crack number and crack spatial distribution.

[0096] In one implementation, the accuracy degradation prediction module 240 includes:

[0097] A time domain spectrum determination unit 241 is used to perform time domain analysis on the winding tension and winding angle of the bearing that vary with time, to obtain a time domain spectrum;

[0098] A feature vector determining unit 242, configured to construct a first feature vector based on each feature in the time domain spectrum;

[0099] A target feature determination unit 243, configured to select at least one target feature in the first feature vector based on a mutual information value between each feature in the first feature vector and the line-receiving accuracy of the bearing;

[0100] An input feature determination unit 244, configured to perform data fusion based on the at least one target feature and the crack extension information to obtain an input feature matrix;

[0101] The degradation degree prediction unit 245 is used to process the input feature matrix based on a long short-term memory network to obtain the degradation degree of the bearing's winding accuracy due to the extended crack of the bearing in the future time.

[0102] In one embodiment, the above system may further include:

[0103] A sample acquisition module, used to acquire a training sample set, wherein each training sample in the training sample set includes historical bearing operation data and historical surface crack information of the bearing sample at a first historical time, and historical crack extension information at a second historical time, wherein the first historical time is earlier than the second historical time;

[0104] The model training module is used to perform the following operations on any of the training samples:

[0105] Inputting the historical bearing operation data and the historical surface crack information in the training sample into the crack growth prediction model to obtain the predicted crack growth information within the second historical time output by the crack growth prediction model;

[0106] Based on the historical crack growth information and the predicted crack growth information within the second historical time, model parameters of the crack growth prediction model are updated.

[0107] In one embodiment, the operating condition adjustment module 250 includes:

[0108] an objective function construction unit, for constructing an objective function by taking the operating condition of the bearing as an independent variable and taking the wire taking-up accuracy and crack growth rate of the bearing as dependent variables when the degradation degree of the wire taking-up accuracy of the bearing is greater than a preset degradation degree threshold;

[0109] An objective function solving unit, used to solve the minimum value of the objective function based on a particle swarm optimization algorithm to obtain a target operating condition of the bearing;

[0110] A bearing operation control unit is used to control the operation of the bearing based on the target operating condition of the bearing.

[0111] According to an embodiment of the present disclosure, the above method of the present disclosure may be applied to an electronic device and a readable storage medium.

[0112] Figure 3 A schematic block diagram of an example electronic device 600 that can be used to implement an embodiment of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present disclosure described and / or required herein.

[0113] like Figure 3As shown, the device 600 includes a computing unit 601, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 602 or a computer program loaded from a storage unit 608 into a random access memory (RAM) 603. In the RAM 603, various programs and data required for the operation of the device 600 can also be stored. The computing unit 601, the ROM 602, and the RAM 603 are connected to each other via a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.

[0114] A number of components in the device 600 are connected to the I / O interface 605, including: an input unit 606, such as a keyboard, a mouse, etc.; an output unit 607, such as various types of displays, speakers, etc.; a storage unit 608, such as a disk, an optical disk, etc.; and a communication unit 609, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 609 allows the device 600 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0115] The computing unit 601 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 601 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 601 performs the various methods and processes described above, such as a ground wire winding and line taking-up control method. For example, in some embodiments, a ground wire winding and line taking-up control method may be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit 608. In some embodiments, part or all of the computer program may be loaded and / or installed on the device 600 via the ROM 602 and / or the communication unit 609. When the computer program is loaded into the RAM 603 and executed by the computing unit 601, one or more steps of a ground wire winding and line taking-up control method described above may be performed. Alternatively, in other embodiments, the computing unit 601 may be configured to execute a ground wire winding and retracting control method in any other appropriate manner (for example, by means of firmware).

[0116] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0117] The program code for implementing the method of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that the program code, when executed by the processor or controller, enables the functions / operations specified in the flow chart and / or block diagram to be implemented. The program code may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0118] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or device, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0119] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0120] The systems and techniques described herein may be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), and the Internet.

[0121] A computer system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The relationship of client and server is generated by computer programs running on respective computers and having a client-server relationship with each other. The server may be a cloud server, a server of a distributed system, or a server combined with a blockchain.

[0122] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps recorded in this disclosure can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved, and this document does not limit this.

[0123] The above specific implementations do not constitute a limitation on the protection scope of the present disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the principles of the present disclosure shall be included in the protection scope of the present disclosure.

Claims

1. A ground wire winding and take-up control method, characterized in that: include: Determining surface crack information of the bearing based on a surface image of the bearing for winding the ground wire; Monitoring the operation process of the bearing to obtain bearing operation data of the bearing; Using a crack propagation prediction model, the bearing operation data and the surface crack information are processed to predict the crack propagation information of the bearing within a preset time in the future; In the case that the crack propagation information does not meet the preset crack propagation requirements, based on the key line-receiving parameters of the bearing and the crack propagation information, the degree of degradation of the line-receiving precision of the bearing caused by the propagation crack of the bearing in the future is predicted, which includes: performing time domain analysis on the line-receiving tension and line-receiving angle that vary with time in the key line-receiving parameters of the bearing to obtain a time domain spectrum; constructing a first feature vector based on each feature in the time domain spectrum; selecting at least one target feature in the first feature vector based on the mutual information value between each feature in the first feature vector and the line-receiving precision of the bearing; Performing data fusion based on the at least one target feature and the crack extension information to obtain an input feature matrix; and processing the input feature matrix based on a long short-term memory network to obtain a degree of degradation of the wire-taking accuracy of the bearing due to the extension crack of the bearing in the future time; Based on the degree of deterioration, the operating condition of the bearing is adjusted to adjust the wire-receiving strategy of the ground wire and control the crack propagation information and key wire-receiving parameters of the bearing.

2. The method according to claim 1, characterized in that The determining of surface crack information of the bearing based on the surface image of the bearing for winding the ground wire comprises: Performing edge calculation on each surface image in the surface image sequence of the bearing to obtain edge features of each surface image; Determining a target surface image in the surface image sequence based on edge features of each of the surface images; Based on the cracks in the target surface image, surface crack information of the bearing is determined, wherein the surface crack information includes crack size, crack quantity and crack spatial distribution.

3. The method according to claim 1, characterized in that Also includes: Acquire a training sample set, wherein each training sample in the training sample set includes historical bearing operation data and historical surface crack information of the bearing sample at a first historical time, and historical crack extension information at a second historical time, wherein the first historical time is earlier than the second historical time; For any of the training samples, perform the following operations: Inputting the historical bearing operation data and the historical surface crack information in the training sample into the crack growth prediction model to obtain the predicted crack growth information within the second historical time output by the crack growth prediction model; Based on the historical crack growth information and the predicted crack growth information within the second historical time, model parameters of the crack growth prediction model are updated.

4. The method according to claim 1, characterized in that The adjusting the operating condition of the bearing based on the degree of degradation includes: When the degradation degree of the wire taking-up accuracy of the bearing is greater than a preset degradation degree threshold, an objective function is constructed with the operating condition of the bearing as an independent variable and the wire taking-up accuracy and crack growth rate of the bearing as dependent variables; Based on the particle swarm optimization algorithm, the minimum value of the objective function is solved to obtain the target operating condition of the bearing; Based on the target operating condition of the bearing, the operation of the bearing is controlled.

5. A ground wire winding and take-up control system, characterized in that: include: A first data determination module, configured to determine surface crack information of the bearing based on a surface image of the bearing for winding and collecting the ground wire; A second data determination module, used for monitoring the operation process of the bearing to obtain bearing operation data of the bearing; An expansion crack prediction module is used to process the bearing operation data and the surface crack information using a crack expansion prediction model to predict the crack expansion information of the bearing within a preset time in the future; An accuracy degradation prediction module, used for predicting the degree of degradation of the bearing's take-up accuracy due to the propagation crack of the bearing in the future based on the key take-up parameters of the bearing and the crack propagation information when the crack propagation information does not meet the preset crack propagation requirements; An operating condition adjustment module, used to adjust the operating condition of the bearing based on the degree of deterioration, so as to adjust the wire-receiving strategy of the ground wire and control the crack propagation information and key wire-receiving parameters of the bearing; Wherein, the accuracy degradation prediction module includes: A time domain spectrum determination unit is used to perform time domain analysis on the winding tension and winding angle of the bearing that vary with time, to obtain a time domain spectrum; A feature vector determination unit, configured to construct a first feature vector based on each feature in the time domain spectrum; a target feature determination unit, configured to select at least one target feature in the first feature vector based on a mutual information value between each feature in the first feature vector and the line-receiving accuracy of the bearing; An input feature determination unit, configured to perform data fusion based on the at least one target feature and the crack extension information to obtain an input feature matrix; The degradation degree prediction unit is used to process the input feature matrix based on a long short-term memory network to obtain the degradation degree of the bearing's winding accuracy due to the extended crack of the bearing in the future time.

6. The system according to claim 5, characterized in that The first data determination module includes: An edge computing unit, used for performing edge computing on each surface image in the surface image sequence of the bearing to obtain edge features of each surface image; a target image determining unit, configured to determine a target surface image in the surface image sequence based on edge features of each of the surface images; A crack information determination unit is used to determine the surface crack information of the bearing based on the cracks in the target surface image, wherein the surface crack information includes crack size, crack number and crack spatial distribution.

7. An electronic device comprising: at least one processor; as well as a memory communicatively coupled to the at least one processor; The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the method described in any one of claims 1 to 4.

8. A non-transitory computer-readable storage medium storing computer instructions, wherein: The computer instructions are used to cause the computer to execute the method according to any one of claims 1-4.

Images