A machine vision cable fixing method, system and device

Abstract

The present application provides a machine vision cable fixing method, system and device, which includes: obtaining cable fixing parameters and collecting cable fixing images during the cable fixing process; using machine vision to perform content recognition on the cable fixing images, identifying and obtaining cable gap parameters, performing fixed cable damage analysis, and obtaining first cable damage parameters; collecting environmental parameters, combining the cable gap parameters to perform cable shaking damage analysis, obtaining cable shaking parameters, and performing shaking cable damage analysis to obtain second cable damage parameters; calculating and obtaining cable damage parameters based on the first and second cable damage parameters, calculating and obtaining a cable fixing score based on the cable shaking parameters, adjusting and optimizing the cable fixing parameters, and obtaining the optimal cable fixing result. This solves the technical problem of low cable fixing quality caused by the extensive cable fixing method in the prior art.

Description

Technical Field

[0001] The present invention relates to the field of machine vision, and in particular to a cable fixing method, system and device for machine vision. Background Art

[0002] The quality of cable fixing directly determines cable performance. Traditional cable fixing methods, lacking quantitative fixing parameters, rely entirely on manual judgment and experience, resulting in significant deviations in 40% of installations. Overtightening can subject the insulation layer to abnormal pressure exceeding 25N / mm², damaging the cable's surface insulation and impacting performance. Overloosening can cause wind-induced vibrations, leading to abrasion of the cable's surface insulation, further impacting performance. Consequently, existing technologies suffer from the technical problem of poor cable fixing quality due to crude cable fixing methods. Summary of the Invention

[0003] The present invention addresses the technical problem in the prior art of extensive cable fixing methods resulting in low cable fixing quality, and provides a machine vision cable fixing method, system and device.

[0004] The technical solution of the present invention to solve the above technical problems is as follows:

[0005] In a first aspect, the present invention provides a machine vision cable fixing method, comprising:

[0006] During the cable fixing process, cable fixing parameters are obtained and cable fixing images are captured;

[0007] Using machine vision to perform content recognition on the cable fixing image, identify and obtain cable gap parameters, perform fixed cable damage analysis, and obtain first cable damage parameters;

[0008] Collecting environmental parameters, performing cable shaking damage analysis in combination with the cable gap parameters to obtain cable shaking parameters, and performing shaking cable damage analysis to obtain second cable damage parameters;

[0009] The cable damage parameter is calculated based on the first cable damage parameter and the second cable damage parameter. The cable fixation score is calculated based on the cable shake parameter. The cable fixation parameters are adjusted and optimized to obtain the optimal cable fixation result.

[0010] In a second aspect, the present invention provides a machine vision system, comprising:

[0011] The data acquisition module is used to obtain cable fixing parameters and capture cable fixing images during the cable fixing process;

[0012] a fixed damage analysis module, configured to use machine vision to perform content recognition on the cable fixed image, identify and obtain cable gap parameters, perform fixed cable damage analysis, and obtain first cable damage parameters;

[0013] a sway damage analysis module, configured to collect environmental parameters, perform cable sway damage analysis based on the cable clearance parameters to obtain cable sway parameters, and classify sway cable damage to obtain second cable damage parameters;

[0014] The optimization output module is used to calculate the cable damage parameter based on the first cable damage parameter and the second cable damage parameter, and calculate the cable fixation score in combination with the cable shaking parameter, and adjust and optimize the cable fixation parameter to obtain the optimal cable fixation result.

[0015] In a third aspect, the present invention provides a machine vision cable fixing device, which includes: a memory for storing a computer software program; and a processor for reading and executing the computer software program, thereby implementing a machine vision cable fixing method.

[0016] The beneficial effects of the present invention are:

[0017] The present application first obtains cable fixing parameters and captures cable fixing images during the cable fixing process, providing reliable data support for the subsequent optimization of cable fixing parameters; secondly, machine vision is used to perform content recognition on the cable fixing images, identify and obtain cable gap parameters, perform fixed cable damage analysis, obtain first cable damage parameters, and establish a correlation between cable gap parameters and insulation layer damage conditions; then, environmental parameters are collected, and cable shaking damage analysis is performed in combination with the cable gap parameters to obtain cable shaking parameters, and shaking cable damage analysis is performed to obtain second cable damage parameters, and establish a correlation between environmental wind parameters and insulation layer damage conditions; finally, based on the first cable damage parameters and the second cable damage parameters, the cable damage parameters are calculated, and combined with the cable shaking parameters, the cable fixing score is calculated, and the cable fixing parameters are adjusted and optimized to obtain the optimal cable fixing result.

[0018] Through the above technical solution, the present application first collects cable fixing parameters and corresponding images during the cable fixing process. Then, based on machine vision technology, it obtains the first cable damage parameter and the second cable damage parameter. It then establishes a correlation between the cable gap parameter, the environmental wind parameters, and the insulation layer damage. Finally, it comprehensively considers the impact of the cable insulation layer damage and the stability of the electrical connection on the cable fixing quality, and continuously optimizes the cable fixing parameters until the optimal cable fixing parameters are output. In this way, the cable fixing quality is improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 A schematic flow chart of a machine vision cable fixing method provided by the present invention;

[0020] Figure 2 A schematic structural diagram of a machine vision cable fixing system provided by the present invention;

[0021] Figure 3 This is a structural schematic diagram of a machine vision cable fixing device provided by the present invention.

[0022] In the accompanying drawings, the components represented by the reference numerals are as follows:

[0023] Data acquisition module 11 , fixation damage analysis module 12 , sway damage analysis module 13 , optimization output module 14 , cable fixing device 200 , memory 210 , processor 220 , computer program 211 . DETAILED DESCRIPTION

[0024] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without making any creative efforts shall fall within the scope of protection of the present invention.

[0025] In the description of the present invention, the terms "first" and "second" are used for descriptive purposes only and should not be understood to indicate or imply relative importance or implicitly specify the number of the technical features indicated. Therefore, a feature specified as "first" or "second" may explicitly or implicitly include one or more of the specified features. In the description of the present invention, "plurality" means two or more, unless otherwise specifically defined.

[0026] In the description of the present invention, the term "for example" is used to mean "used as an example, illustration or illustration". Any embodiment of the present invention described as "for example" is not necessarily to be construed as being more preferred or advantageous than other embodiments. The following description is given to enable any person skilled in the art to implement and use the present invention. In the following description, details are listed for the purpose of explanation. It should be understood that a person of ordinary skill in the art can recognize that the present invention can be implemented without using these specific details. In other examples, well-known structures and processes are not elaborated in detail to avoid obscuring the description of the present invention with unnecessary details. Therefore, the present invention is not intended to be limited to the embodiments shown, but is consistent with the widest scope consistent with the principles and features disclosed herein.

[0027] Example 1, as Figure 1As shown, an embodiment of the present invention provides a machine vision cable fixing method, comprising:

[0028] S10: During the cable fixing process, obtaining cable fixing parameters and capturing cable fixing images;

[0029] Traditional cable securing is primarily accomplished manually using devices like cable clamps and cable ties. However, due to the lack of standardized securing parameters (such as the travel distance of the bolts within the cable clamp and the gap between the cable tie and the cable), these traditional methods rely entirely on manual skill and experience, resulting in poor cable securing quality.

[0030] To address the above issues, the present application obtains cable fixing parameters during the process of fixing the cable, and obtains corresponding cable fixing images based on the cable fixing parameters, providing necessary data support for subsequent optimization of the fixing parameters.

[0031] Specifically, step S10 in the method includes:

[0032] During the process of fixing the cable, obtaining cable fixing parameters, wherein the cable fixing parameters include fixing dimensions;

[0033] An image of the cable after being fixed according to the cable fixing parameters is collected to obtain a cable fixing image.

[0034] In this embodiment, the cable fixing parameters during the cable fixing process are first acquired, where these cable fixing parameters include fixing dimensions. Specifically, the cable is primarily secured using fixing devices such as cable clamps and cable ties. The fixing dimensions during the cable fixing process (such as the rotational distance of the bolts within the cable clamp and the gap between the cable tie and the cable) are captured and used as the cable fixing parameters. For example, when securing the cable using a cable clamp, the rotational distance of the bolts within the cable clamp is captured as 4.5 mm, which is used as the cable fixing parameter.

[0035] Secondly, an image of the cable after being fixed according to the cable fixing parameters is captured to obtain a cable fixing image. For example, a 20-megapixel industrial camera (such as Basler ace) is used to capture the cable fixing image corresponding to the fixing parameters.

[0036] In summary, the present application first collects the cable fixing parameters during the cable fixing process, and then collects the cable fixing images corresponding to the cable fixing parameters, so as to provide reliable data support for the subsequent optimization of the cable fixing parameters.

[0037] S20: Using machine vision to perform content recognition on the cable fixed image, identify and obtain cable gap parameters, perform fixed cable damage analysis, and obtain first cable damage parameters;

[0038] During the cable fixing process, if the cable is fixed too tightly, it will cause damage to the cable insulation layer. For example, when the pressure applied by the fixing equipment exceeds the yield strength of the material, it will cause local thinning of the insulation layer. During long-term operation, radial crack networks will form in the areas where mechanical stress is concentrated, thereby affecting the cable performance and shortening the cable service life.

[0039] To address the above problems, this application is based on machine vision. By analyzing the relationship between the cable gap parameters and the damage size of the cable insulation layer, the association between the cable fixing parameters and the cable damage is established. The cable gap parameters are then input into the first cable damage classifier to obtain the first cable damage parameters as output.

[0040] Specifically, step S20 in the method includes:

[0041] Preprocessing the cable fixing image;

[0042] The preprocessed cable fixing image is input into a pretrained cable fixing identifier to identify and output cable gap parameters, wherein the cable gap parameters include the gap distance after the cable is fixed. The cable fixing identifier is constructed using a convolutional neural network and is trained using a set of sample cable fixing images and a set of sample cable gap parameters.

[0043] In this embodiment, the captured cable fixing image is first preprocessed. For example, Gaussian and median filtering are used to eliminate image noise; the CLAHE algorithm is used for adaptive illumination equalization to address uneven illumination; Canny edge detection and the Sobel operator are used to enhance cable contour features; and morphological operations are used to extract key areas. The preprocessed image undergoes geometric standardization and normalization, ultimately converting it into a tensor format suitable for convolutional neural network input. This provides high-quality input data for subsequent cable clearance parameter identification and output.

[0044] Next, the preprocessed cable fixation images are input into a trained cable fixation identifier, which outputs the gap distance after cable fixation as the cable gap parameter. The cable gap parameter is a quantifiable parameter, such as the maximum distance between the cable and the fixture after fixation. The cable fixation identifier is constructed using a convolutional neural network (CNN) and trained using a set of sample cable fixation images and a set of sample cable gap parameters. The construction and training process of the cable fixation identifier is as follows: 1. Acquiring a training dataset: Preprocessed cable fixation images are collected as the sample cable fixation image set. The images are manually labeled with cable gap parameters (using an annotation tool such as LabelImg) to form the sample cable gap parameter set. The dataset is then divided into a training set, a validation set, and a test set in a ratio of 7.5:1.5:1.5. 2. Model construction: The cable fixation identifier is constructed using a multi-layer convolutional neural network (CNN), consisting of five convolutional layers, three pooling layers, and two fully connected layers. Reluctant Unit (ReLU) activation functions and batch normalization are used for efficient feature extraction. 3. Model training: Using transfer learning, we used a pre-trained ResNet50 model as the base model and fine-tuned it using a dataset of 5,000 labeled samples. We optimized the model parameters using the Adam optimizer and a cosine annealing learning rate scheduling strategy, ultimately achieving a recognition accuracy of 95% on the test set.

[0045] For example, 5,000 cable fixation images were collected, de-noised, enhanced, and normalized to form a sample cable fixation image set. Each image was manually labeled with gap parameters using the LabelImg tool to form a sample cable gap parameter set. The sample cable fixation image set and the sample cable gap parameter set were divided into training, validation, and test sets in a ratio of 7.5:1.5:1.5. A cable fixation identifier based on a convolutional neural network (CNN) was then trained and optimized until the output achieved 95% recognition accuracy on the test set, indicating model convergence. The preprocessed cable fixation images were then fed into the trained cable fixation identifier, which outputs the maximum gap between the fixed cable and the fixture (e.g., 2 mm) as the cable gap parameter.

[0046] Furthermore, the “performing a fixed cable damage analysis to obtain a first cable damage parameter” includes:

[0047] Based on the cable fixing data in the historical time, a sample cable gap parameter set is collected, and the size of the cable insulation layer damage under different sample cable gap parameters is collected and marked as the sample first cable damage parameter to obtain the sample first cable damage parameter set;

[0048] Constructing an index relationship between the sample cable clearance parameter set and the sample first cable damage parameter set to obtain a first cable damage classifier;

[0049] The cable gap parameter is input into the first cable damage classifier, and the index classification output is obtained to obtain the first cable damage parameter.

[0050] In an embodiment of the present application, first, based on the cable fixing data in the historical period, a sample cable gap parameter set (such as the maximum distance of the gap between the cable and the fixing device after fixing, mm) is collected, and the size of the cable insulation layer damage under different sample cable gap parameters (such as the length direction dimension of the insulation layer damage, the thickness direction dimension of the insulation layer damage, mm) is collected, and marked as the sample first cable damage parameter, and the sample first cable damage parameter set is obtained. For example, a certain cable is fixed with a cable tie, and the maximum distance of the gap between the cable and the cable tie is collected by a digital micrometer, which is 2.1mm, 1.9mm, 1.6mm, 2mm, and 1.3mm, respectively, as the sample cable gap parameter set. Then, the thickness direction dimensions of the cable insulation layer damage corresponding to different gap parameters are collected by an ultrasonic thickness gauge, which are 0.8mm, 0.76mm, 0.6mm, 0.77mm, and 0.4mm, respectively, and marked as the sample first cable damage parameter, and the sample first cable damage parameter set is obtained.

[0051] Secondly, an index relationship between the sample cable gap parameter set and the sample first cable damage parameter set is constructed to obtain a first cable damage classifier. For example, a one-to-one corresponding index relationship is established between the aforementioned sample cable gap parameter set [2.1mm, 1.9mm, 1.6mm, 2mm, 1.3mm] and the sample first cable damage parameter set [0.8mm, 0.76mm, 0.6mm, 0.77mm, 0.4mm]. Furthermore, the construction and training process of the first cable damage classifier can be achieved through the following technical paths: 1. Prepare a training data set: prepare 5,000 groups of corresponding sample cable gap parameter sets and sample first cable damage parameter sets, and divide them into training set, validation set, and test set in a ratio of 7.5:1.5:1.5. 2. Model Construction: A Mixture of Experts (MoE) architecture is employed, primarily comprising a feature extraction module, a spatial attention module, and a decision fusion module. The feature extraction module uses a 1D-CNN to process time series signals (sampling rate 1kHz) and a GRU network to capture long-term dependencies. The spatial attention module utilizes a CBAM mechanism to enhance key positional features. The decision fusion module integrates the dual outputs of XGBoost (max_depth=6) and LightGBM (num_leaves=31). 3. Model Training: The training process utilizes a curriculum learning strategy. The model is first trained on the training set, then fine-tuned by augmenting difficult samples with a Generative Adversarial Network (GAN). A Bayesian hyperparameter search is introduced during the model optimization phase. Ultimately, achieving 95% accuracy on the test set is considered model convergence.

[0052] Finally, the cable gap parameter is input into the trained first cable damage classifier, and the index classification output is used to obtain the first cable damage parameter. For example, the cable gap parameter of 2.2 mm is input into the trained first cable damage classifier, and the output is the first cable damage parameter of 0.32 mm.

[0053] In summary, compared to existing technologies, this application uses machine vision to perform content recognition on fixed cable images to identify cable gap parameters. Using a first cable damage classifier, this method performs fixed cable damage analysis for different cable gap parameters to obtain the first cable damage parameter. This establishes a correlation between cable gap parameters and insulation layer damage, providing reliable data support for subsequent optimization of fixed parameters.

[0054] S30: collecting environmental parameters, performing cable shaking damage analysis in combination with the cable gap parameters to obtain cable shaking parameters, and performing shaking cable damage analysis to obtain second cable damage parameters;

[0055] If the cable is fixed too loosely, it can swing in the wind, causing friction and damaging the cable insulation. Specifically, the constant reciprocating motion between the cable surface and the mounting device can cause abrasive wear on the insulation, affecting cable performance and shortening its service life.

[0056] To address the above problems, the present application collects wind parameters in the cable fixing environment as environmental parameters, then inputs the environmental parameters into a cable sway predictor constructed based on a feedforward neural network, outputs cable sway parameters, and then inputs the cable sway parameters into a second cable damage classifier to obtain the second cable damage parameters.

[0057] Specifically, step S30 in the method includes:

[0058] Collect wind parameters in the cable fixing environment as environmental parameters;

[0059] The cable clearance parameters and environmental parameters are input into a pre-trained cable sway predictor to predict and output cable sway parameters, wherein the cable sway parameters include the sway distance of the cable per unit time. The cable sway predictor is constructed based on a feedforward neural network and is trained using a sample cable clearance parameter set, a sample environmental parameter set, and a sample cable sway parameter set.

[0060] In this embodiment, wind parameters within the cable's fixed environment are first collected as environmental parameters. These environmental parameters, such as average wind speed, wind direction, and eddy currents, serve as primary environmental factors affecting cable vibration damage. For example, an average wind speed of 1.8 m / s is collected within the cable's fixed environment as an environmental parameter.

[0061] Next, the cable clearance parameters and environmental parameters are input into the trained cable sway predictor, which outputs the cable sway distance per unit time as the cable sway parameter. The cable sway parameter is the cable sway distance per unit time, for example, in mm / s or cm / min. The cable sway predictor is constructed using a feedforward neural network and trained using a sample set of cable clearance parameters, a sample set of environmental parameters, and a sample set of cable sway parameters. Furthermore, the cable sway predictor is constructed and trained as follows: 1. Collecting a training dataset: Wind parameters under different wind conditions (e.g., average ambient wind speed, m / s) are collected as a sample environmental parameter set. Cable clearance data under different fixed states under the corresponding wind conditions (e.g., the maximum distance between the cable and the fixed equipment after fixing, mm) are collected as a sample cable clearance parameter set. Finally, cable sway distances under the corresponding wind conditions and corresponding cable clearance distances are collected (e.g., the actual measured cable sway distance per unit time, mm / s) as a sample cable sway parameter set. The dataset is then divided into a training set, a validation set, and a test set in a ratio of 7.5:1.5:1.5. 2. Model construction: The cable sway predictor is constructed using a feedforward neural network with physical constraints. The input layer receives a 15-dimensional feature vector, consists of three hidden layers of 128 nodes (with a dropout rate of 0.3), and a linear output layer. It is optimized using a hybrid loss function (L1+L2+physical constraint term). 3. Model training: The training process adopts a transfer learning strategy, first pre-training based on the sample training set, then fine-tuning using the validation set data, and ultimately achieving a recognition accuracy of 95% on the test set.

[0062] For example, the average wind speed under different environments (e.g., 2.5 m / s, 3.0 m / s, 3.5 m / s, 4.0 m / s, and 4.5 m / s) is collected as a sample environmental parameter set. Cable clearance data under different fixed states under these environmental parameters is then collected (e.g., under 2.5 m / s, cable clearance data of 2.1 mm, 1.9 mm, 1.6 mm, 2 mm, and 1.3 mm is collected as a sample cable clearance parameter set). Finally, the cable sway distance per unit time under these environmental parameters and corresponding cable clearance distance conditions is collected (e.g., under 2.5 m / s and a cable clearance of 2.1 mm, a sway distance per unit time of 1.6 mm / s is collected as a sample cable sway parameter set). This dataset is then divided into training, validation, and test sets in a ratio of 7.5:1.5:1.5. The cable sway predictor is then trained and optimized until the output data reaches 95% recognition accuracy on the test set, which is considered model convergence. Finally, the cable gap parameters (e.g., 2.1 mm) and environmental parameters (e.g., 2.5 m / s) are input into the trained cable sway predictor, which outputs the cable sway distance per unit time (e.g., 1.6 mm / s) as the cable sway parameter.

[0063] Furthermore, the “performing a shaking cable damage analysis to obtain a second cable damage parameter” includes:

[0064] Based on the cable monitoring data in the historical period, a sample cable sway parameter set is collected, and the damage size of the cable insulation layer within a preset time range under different sample cable sway parameters is collected and marked as the sample second cable damage parameter to obtain the sample second cable damage parameter set;

[0065] Constructing an index relationship between the sample cable shake parameter set and the sample second cable damage parameter set to obtain a second cable damage classifier;

[0066] The cable shaking parameter is input into the second cable damage classifier, and the index classification output is obtained to obtain the second cable damage parameter.

[0067] In an embodiment of the present application, a sample cable sway parameter set (the cable's sway distance per unit time, in mm / s, cm / min) is first collected based on historical cable monitoring data. The dimensions of the cable insulation damage within a preset time range (e.g., the longitudinal dimension of the insulation damage, the thickness dimension of the insulation damage, in mm) are then collected under different sample cable sway parameters. These dimensions are labeled as sample second cable damage parameters, thereby obtaining a sample second cable damage parameter set. The preset time range is a time range determined by one skilled in the art based on practical circumstances, such as 1 month, 6 months, or 12 months. For example, for a cable laid outdoors, its sway parameters (1.6 mm / s, 1.4 mm / s, 1.2 mm / s, 1.0 mm / s, and 0.8 mm / s) are collected. The thickness dimensions of the insulation damage under different cable sway parameters (e.g., 0.21 mm, 0.19 mm, 0.16 mm, 0.15 mm, and 0.12 mm) are then collected and labeled as sample second cable damage parameters, thereby obtaining a sample second cable damage parameter set.

[0068] Secondly, an index relationship between the sample cable swing parameter set and the sample second cable damage parameter set is constructed to obtain a second cable damage classifier. For example, a one-to-one corresponding index relationship is established between the aforementioned sample cable swing parameter set [1.6mm / s, 1.4mm / s, 1.2mm / s, 1.0mm / s, 0.8mm / s] and the sample second cable damage parameter set [0.21mm, 0.19mm, 0.16mm, 0.15mm, 0.12mm]. Furthermore, the construction and training process of the second cable damage classifier can be achieved through the following technical paths: 1. Prepare a training data set: prepare a sample cable swing parameter set and a sample second cable damage parameter set, and divide them into a training set, a validation set, and a test set in a ratio of 7.5:1.5:1.5. 2. Model construction: adopt the dual-track design concept of "physical mechanism driven + data driven", and achieve high-precision damage classification through a three-layer cascaded LSTM-Attention hybrid neural network. The model input layer receives the feature vector (including the vibration parameters). After the bidirectional LSTM layer extracts the temporal features, a self-attention mechanism dynamically focuses on the key vibration periods. Finally, the output (the second cable damage parameter) is obtained through a global max-pooling and regularized fully connected layer. 3. Model Training: The training process adopts a curriculum learning strategy. The model is first trained on the training set, then fine-tuned by augmenting difficult samples using a Generative Adversarial Network (GAN). Bayesian hyperparameter search is introduced during the model optimization phase. The model is considered converged when an accuracy of 95% is achieved on the test set.

[0069] Finally, the cable swing parameter is input into the second cable damage classifier, and the index classification output is used to obtain the second cable damage parameter. For example, the cable swing parameter of 1.6 mm / s is input into the trained second cable damage classifier, and the output obtained second cable damage parameter is 0.21 mm.

[0070] In summary, compared to existing technologies, this application collects environmental parameters and combines them with the cable clearance parameters to perform cable sway damage analysis, obtaining cable sway parameters. Furthermore, this analysis performs cable sway damage analysis to obtain a second cable damage parameter. This establishes a correlation between environmental wind-induced parameters and insulation layer damage, providing reliable data support for subsequent optimization of fixed parameters.

[0071] S40: Calculate a cable damage parameter based on the first cable damage parameter and the second cable damage parameter, calculate a cable fixation score based on the cable shake parameter, and adjust and optimize the cable fixation parameter to obtain an optimal cable fixation result.

[0072] The first and second cable damage parameters reflect the relationship between cable fixing parameters and insulation damage. Adjusting the cable fixing parameters can improve insulation damage and enhance cable fixing quality. Furthermore, in natural environments, cable fixing quality is not only affected by surface insulation damage, but also by the stability of the electrical connection. Specifically, wind-induced cable movement can affect the stability of the electrical connection, which in turn affects cable fixing quality.

[0073] In response to the above problems, this application is based on the aforementioned first cable damage parameter and second cable damage parameter, while taking into account the impact of the damage to the cable insulation layer and the stability of the electrical connection on its fixing quality. By calculating the cable fixing score, the cable fixing parameters are continuously optimized until the optimal cable fixing parameters are output.

[0074] Specifically, step S40 in the method includes:

[0075] Calculating a cable damage parameter based on the first cable damage parameter and the second cable damage parameter;

[0076] According to the cable damage parameters and cable shaking parameters, the cable fixation score is calculated as follows:

[0077] ;

[0078] Among them, FIHG is the cable fixing score, and is the weight, is the cable damage parameter, The preset size of the cable insulation layer, D is the cable sway parameter, To preset the cable shaking parameters;

[0079] Adjusting the cable fixing parameters to obtain adjusted cable fixing parameters, and performing analysis and calculation to obtain a cable fixing score;

[0080] Iteratively adjust and optimize the cable fixing parameters until convergence, output the optimal cable fixing parameters with the largest cable fixing score, fix the cable, and obtain the optimal cable fixing result.

[0081] In the embodiment of the present application, the cable damage parameter is first calculated based on the first and second cable damage parameters. The cable damage parameter is calculated as follows: the first cable damage parameter + the second cable damage parameter. For example, if the first cable damage parameter is 0.13 mm and the second cable damage parameter is 0.09 mm, then the cable damage parameter = 0.13 mm + 0.09 mm = 0.22 mm.

[0082] Secondly, based on the cable damage parameters and cable sway parameters, the cable fixation score is calculated using the following formula:

[0083] ;

[0084] Where FIHG is the cable fixation score. The higher the fixation score, the higher the cable fixation quality. w1 and w2 are weights (w1+w2=1). The initial values ​​of w1 and w2 are determined by those skilled in the art based on actual conditions, such as setting w1=0.6 and w2=0.4. s is the cable damage parameter, C s The smaller the value (indicating less damage to the cable insulation layer), the greater the cable fixation score. y The preset size of the cable insulation layer, that is, the initial thickness of the cable insulation layer. For example, the standard insulation layer thickness of the medium voltage cable is 4.5mm. D is the cable sway parameter. The smaller D is (the smaller the sway, the more stable the electrical connection), the greater the cable fixation score. y The preset cable shaking parameter is the maximum allowed cable shaking parameter. For example, if the maximum allowed cable shaking distance per unit time is 0.5 mm / s, then D y Set to 0.5mm / s.

[0085] For example, w1 and w2 are 0.6 and 0.4 respectively, C s 0.53mm, C y is 4.5mm, D is 0.3mm / s, D y is 0.5 mm / s, substitute into the above formula to calculate:

[0086] =0.557+0.089=0.645.

[0087] For example, w1 and w2 are 0.6 and 0.4 respectively, Cs is 0.8 mm, Cy is 4.5 mm, D is 0.45 mm / s, and Dy is 0.5 mm / s. Substitute them into the above formula for calculation:

[0088] =0.525+0.018=0.543. It can be seen that when the cable damage parameter and the cable sway parameter decrease, the cable fixation score increases.

[0089] Thirdly, the cable fixing parameters are adjusted to obtain the adjusted cable fixing parameters, and a new cable fixing score is calculated. Specifically, adjusting the cable fixing parameters will result in a cable damage parameter C s Changes in the cable sway parameter D, and thus the cable fixation score (FIHG), change accordingly. For example, if the initial value of the cable fixation parameter (e.g., the travel distance of the bolt in the cable clamp) is 4.5 mm, the calculated FIHG is 0.73. Now, if the cable fixation parameter is increased by 0.2 mm, the new FIHG is recalculated to be 0.82.

[0090] Finally, the cable fixing parameters are iteratively adjusted and optimized until convergence. The optimal cable fixing parameters with the highest cable fixing score are output, and the cable fixing is performed to obtain the optimal cable fixing result. The iterative optimization process can utilize an improved genetic algorithm. Each round of iterative adjustment of the fixing parameters (e.g., the rotation distance of the bolt in the cable clamp by ±0.5mm, the gap distance between the cable tie and the cable by ±0.2mm) is calculated, and a new FIHG value is calculated. This process continues until the FIHG value calculated after five consecutive iterations improves by less than 1%, or until the maximum number of iterations (e.g., 100) is reached. The iterations are terminated, and the optimal cable fixing parameters with the highest cable fixing score are output. Cable fixing is then performed using this optimal value to obtain the optimal cable fixing result.

[0091] In summary, compared to existing technologies, this application simultaneously considers the impact of cable insulation damage and electrical connection stability on cable fixation quality. By calculating a cable fixation score and continuously optimizing cable fixation parameters until the optimal cable fixation parameters are output, the optimal cable fixation result is achieved.

[0092] In summary, the embodiments of the present application have at least the following technical effects:

[0093] Compared with the existing technology, the present application first collects the cable fixing parameters during the cable fixing process, and then collects the cable fixing images corresponding to the cable fixing parameters, thereby providing reliable data support for the subsequent optimization of the cable fixing parameters.

[0094] Next, machine vision is used to identify the content of the fixed cable image and obtain the cable gap parameters. Using the first cable damage classifier, fixed cable damage analysis is performed on different cable gap parameters to obtain the first cable damage parameter. This establishes a correlation between the cable gap parameter and insulation layer damage.

[0095] Next, by collecting environmental parameters and combining them with the cable gap parameters, cable sway damage analysis is performed to obtain cable sway parameters, and then sway cable damage classification is performed to obtain second cable damage parameters. In this way, a correlation is established between environmental wind parameters and insulation layer damage.

[0096] Finally, the effects of cable insulation damage and electrical connection stability on cable fixation quality were considered simultaneously. The cable fixation score was calculated and the cable fixation parameters were continuously optimized until the optimal cable fixation parameters were output. This resulted in the optimal cable fixation parameters.

[0097] Through the above technical solution, the present application first collects the cable fixing parameters and corresponding images during the cable fixing process. Then, based on machine vision technology, it obtains the first cable damage parameter and the second cable damage parameter. It then establishes a correlation between the cable gap parameter, the environmental wind parameters, and the insulation layer damage. Finally, it comprehensively considers the impact of the cable insulation layer damage and the stability of the electrical connection on the cable fixing quality, and continuously optimizes the cable fixing parameters until the optimal cable fixing parameters are output. In this way, the cable fixing quality is improved.

[0098] Example 2, as Figure 2 As shown, based on the same inventive concept of a machine vision cable fixing method provided in Example 1, an embodiment of the present invention further provides a machine vision system, including:

[0099] The data acquisition module 11 is used to obtain cable fixing parameters and capture cable fixing images during the cable fixing process;

[0100] A fixed damage analysis module 12 is configured to use machine vision to perform content recognition on the cable fixed image, identify and obtain cable gap parameters, perform fixed cable damage analysis, and obtain first cable damage parameters;

[0101] The sway damage analysis module 13 is used to collect environmental parameters, perform cable sway damage analysis in combination with the cable gap parameters to obtain cable sway parameters, and perform sway cable damage classification to obtain second cable damage parameters;

[0102] The optimization output module 14 is used to calculate the cable damage parameter based on the first cable damage parameter and the second cable damage parameter, and calculate the cable fixation score in combination with the cable shaking parameter, and adjust and optimize the cable fixation parameter to obtain the optimal cable fixation result.

[0103] The data acquisition module 11 is specifically used for:

[0104] During the process of fixing the cable, obtaining cable fixing parameters, wherein the cable fixing parameters include fixing dimensions;

[0105] An image of the cable after being fixed according to the cable fixing parameters is collected to obtain a cable fixing image.

[0106] The fixed damage analysis module 12 is specifically configured to:

[0107] Preprocessing the cable fixing image;

[0108] The preprocessed cable fixing image is input into a pretrained cable fixing identifier to identify and output cable gap parameters, wherein the cable gap parameters include the gap distance after the cable is fixed. The cable fixing identifier is constructed using a convolutional neural network and is trained using a set of sample cable fixing images and a set of sample cable gap parameters.

[0109] Furthermore, the “performing a fixed cable damage analysis to obtain a first cable damage parameter” includes:

[0110] Based on the cable fixing data in the historical time, a sample cable gap parameter set is collected, and the size of the cable insulation layer damage under different sample cable gap parameters is collected and marked as the sample first cable damage parameter to obtain the sample first cable damage parameter set;

[0111] Constructing an index relationship between the sample cable clearance parameter set and the sample first cable damage parameter set to obtain a first cable damage classifier;

[0112] The cable gap parameter is input into the first cable damage classifier, and the index classification output is obtained to obtain the first cable damage parameter.

[0113] The shaking damage analysis module 13 is specifically used to:

[0114] Collect wind parameters in the cable fixing environment as environmental parameters;

[0115] The cable clearance parameters and environmental parameters are input into a pre-trained cable sway predictor to predict and output cable sway parameters, wherein the cable sway parameters include the sway distance of the cable per unit time. The cable sway predictor is constructed based on a feedforward neural network and is trained using a sample cable clearance parameter set, a sample environmental parameter set, and a sample cable sway parameter set.

[0116] Furthermore, the “classifying the shaking cable damage and obtaining the second cable damage parameter” includes:

[0117] Based on the cable monitoring data in the historical period, a sample cable sway parameter set is collected, and the damage size of the cable insulation layer within a preset time range under different sample cable sway parameters is collected and marked as the sample second cable damage parameter to obtain the sample second cable damage parameter set;

[0118] Constructing an index relationship between the sample cable shake parameter set and the sample second cable damage parameter set to obtain a second cable damage classifier;

[0119] The cable shaking parameter is input into the second cable damage classifier, and the index classification output is obtained to obtain the second cable damage parameter.

[0120] The optimization output module 14 is specifically configured to:

[0121] Calculating a cable damage parameter based on the first cable damage parameter and the second cable damage parameter;

[0122] According to the cable damage parameters and cable shaking parameters, the cable fixation score is calculated as follows:

[0123] ;

[0124] Among them, FIHG is the cable fixing score, and is the weight, is the cable damage parameter, The preset size of the cable insulation layer, D is the cable sway parameter, To preset the cable shaking parameters;

[0125] Adjusting the cable fixing parameters to obtain adjusted cable fixing parameters, and performing analysis and calculation to obtain a cable fixing score;

[0126] Iteratively adjust and optimize the cable fixing parameters until convergence, output the optimal cable fixing parameters with the largest cable fixing score, fix the cable, and obtain the optimal cable fixing result.

[0127] In summary, the embodiments of the present application have at least the following technical effects:

[0128] The data acquisition module collects cable fixing parameters during the cable fixing process and then captures the corresponding cable fixing images, providing reliable data support for subsequent optimization of cable fixing parameters. The fixing damage analysis module uses a first cable damage classifier to analyze the fixing cable damage for different cable gap parameters, obtaining the first cable damage parameter. This parameter is then correlated with insulation damage, providing reliable data support for subsequent optimization of fixing parameters. The sway damage analysis module collects environmental parameters and combines them with cable gap parameters to analyze cable sway damage, obtaining the cable sway parameter. It then classifies the sway cable damage and obtains the second cable damage parameter. This parameter is then correlated with insulation damage, providing reliable data support for subsequent optimization of fixing parameters. The optimization output module considers the impact of cable insulation damage and electrical connection stability on performance, calculates a cable fixing score, and continuously optimizes the cable fixing parameters until the optimal cable fixing parameters are output. This results in optimal cable fixing parameters and improved cable fixing quality.

[0129] like Figure 3 As shown, an embodiment of the present invention provides a machine vision cable fixing device, which includes: a memory 210 for storing a computer software program 211; a processor 220 for reading and executing the computer software program 211, thereby implementing a machine vision cable fixing method.

[0130] It should be noted that, in the above embodiments, the description of each embodiment has its own focus. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant description of other embodiments.

[0131] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Thus, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0132] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowcharts and / or block diagrams, as well as combinations of processes and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded computer, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowcharts and / or block diagrams. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0133] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0134] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0135] Although preferred embodiments of the present invention have been described, additional changes and modifications to these embodiments may occur to those skilled in the art once the basic inventive concepts become known.

[0136] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the present invention and its equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A machine vision cable fixing method, characterized in that: The method comprises: During the cable fixing process, cable fixing parameters are obtained and cable fixing images are captured; Using machine vision to perform content recognition on the cable fixing image, identify and obtain cable gap parameters, perform fixed cable damage analysis, and obtain first cable damage parameters; Collecting environmental parameters, performing cable shaking damage analysis in combination with the cable gap parameters to obtain cable shaking parameters, and performing shaking cable damage analysis to obtain second cable damage parameters; Calculating a cable damage parameter based on the first cable damage parameter and the second cable damage parameter, and calculating a cable fixation score based on the cable sway parameter, adjusting and optimizing the cable fixation parameters to obtain an optimal cable fixation result; During the cable fixing process, obtaining cable fixing parameters and capturing cable fixing images include: During the process of fixing the cable, obtaining cable fixing parameters, wherein the cable fixing parameters include fixing dimensions; collecting an image of the cable after being fixed according to the cable fixing parameters to obtain a cable fixing image; The method of using machine vision to perform content recognition on the cable fixing image to obtain the cable gap parameters includes: Preprocessing the cable fixing image; Inputting the preprocessed cable fixing image into a pretrained cable fixing identifier to identify and output cable gap parameters, wherein the cable gap parameters include the gap distance after the cable is fixed. The cable fixing identifier is constructed using a convolutional neural network and is trained using a set of sample cable fixing images and a set of sample cable gap parameters. The fixed cable damage analysis is performed to obtain the first cable damage parameter, including: Based on the cable fixing data in the historical time, a sample cable gap parameter set is collected, and the size of the cable insulation layer damage under different sample cable gap parameters is collected and marked as the sample first cable damage parameter to obtain the sample first cable damage parameter set; Constructing an index relationship between the sample cable clearance parameter set and the sample first cable damage parameter set to obtain a first cable damage classifier; The cable gap parameter is input into the first cable damage classifier, and the index classification output is obtained to obtain the first cable damage parameter.

2. The cable fixing method for machine vision according to claim 1, characterized in that: Collect environmental parameters and perform cable sway damage analysis in combination with the cable clearance parameters to obtain cable sway parameters, including: Collect wind parameters in the cable fixing environment as environmental parameters; The cable clearance parameters and environmental parameters are input into a pre-trained cable sway predictor to predict and output cable sway parameters, wherein the cable sway parameters include the sway distance of the cable per unit time. The cable sway predictor is constructed based on a feedforward neural network and is trained using a sample cable clearance parameter set, a sample environmental parameter set, and a sample cable sway parameter set.

3. The cable fixing method for machine vision according to claim 1, characterized in that: Perform cable shaking damage classification and obtain the second cable damage parameters, including: Based on the cable monitoring data in the historical period, a sample cable sway parameter set is collected, and the damage size of the cable insulation layer within a preset time range under different sample cable sway parameters is collected and marked as the sample second cable damage parameter to obtain the sample second cable damage parameter set; Constructing an index relationship between the sample cable shake parameter set and the sample second cable damage parameter set to obtain a second cable damage classifier; The cable shaking parameter is input into the second cable damage classifier, and the index classification output is obtained to obtain the second cable damage parameter.

4. The cable fixing method for machine vision according to claim 1, characterized in that: The method includes calculating a cable damage parameter based on the first cable damage parameter and the second cable damage parameter, calculating a cable fixation score based on the cable sway parameter, and adjusting and optimizing the cable fixation parameters to obtain an optimal cable fixation result, including: Calculating a cable damage parameter based on the first cable damage parameter and the second cable damage parameter; According to the cable damage parameters and cable shaking parameters, the cable fixation score is calculated as follows: ； in, Score the cable retention, and is the weight, is the cable damage parameter, Preset size for cable insulation, is the cable sway parameter, To preset the cable shaking parameters; Adjusting the cable fixing parameters to obtain adjusted cable fixing parameters, and performing analysis and calculation to obtain a cable fixing score; Iteratively adjust and optimize the cable fixing parameters until convergence, output the optimal cable fixing parameters with the largest cable fixing score, fix the cable, and obtain the optimal cable fixing result.

5. A machine vision cable fixing system, characterized in that: Used to perform the method according to any one of claims 1 to 4, comprising: The data acquisition module is used to obtain cable fixing parameters and capture cable fixing images during the cable fixing process; a fixed damage analysis module, configured to use machine vision to perform content recognition on the cable fixed image, identify and obtain cable gap parameters, perform fixed cable damage analysis, and obtain first cable damage parameters; a sway damage analysis module, configured to collect environmental parameters, perform cable sway damage analysis based on the cable clearance parameters to obtain cable sway parameters, and classify sway cable damage to obtain second cable damage parameters; The optimization output module is used to calculate the cable damage parameter based on the first cable damage parameter and the second cable damage parameter, and calculate the cable fixation score in combination with the cable shaking parameter, and adjust and optimize the cable fixation parameter to obtain the optimal cable fixation result.

6. A machine vision cable fixing device, characterized in that: include: Memory for storing computer software programs; A processor is used to read and execute the computer software program, thereby implementing the machine vision cable fixing method according to any one of claims 1 to 4.

Images