Automatic copper pipe cutting method and system based on visual guidance

Abstract

The invention discloses an automatic copper pipe cutting method and system based on visual guidance, and particularly relates to the technical field of automatic copper pipe cutting. A high-frame-rate infrared camera is used for collecting heat radiation textures in the automatic copper pipe cutting process, features are extracted through wavelet transform and an optical flow algorithm, signals are enhanced through a generative adversarial network, and the cutting precision is improved. A multi-scale copper pipe thermal stress distribution model is constructed, a thermal stress distribution diagram is generated in real time, a dynamic threshold value is corrected, and self-adaptive cutting is achieved in combination with a Bezier curve algorithm; on the basis of dynamic utilization of heat radiation textures, multi-scale heat effect coupling and morphological evolution threshold optimization, cutting precision and environmental adaptability are improved, and the problem that in the copper pipe cutting process, when the heat radiation textures generated due to local heating serve as visual guidance information, the heat radiation textures cannot be visually guided is solved. And due to randomness and instantaneity of thermal radiation textures, a visual system is difficult to stably extract effective features, so that the cutting path optimization reliability is influenced.

Description

Technical Field

[0001] The present invention relates to the technical field of automatic copper tube cutting, and more specifically, to a method and system for automatic copper tube cutting based on vision guidance. Background Art

[0002] In the industrial production of automatic copper tube cutting, the temperature in the cutting area quickly rises from room temperature to a local maximum of over 500°C. The infrared camera can capture the thermal radiation texture generated by local heating. This texture reflects the temperature distribution and thermal stress state of the copper tube in the form of light and dark changes, providing potential visual guidance information for dynamic optimization of the cutting path. Compared with traditional cutting methods that rely on preset marks, the use of thermal radiation textures does not require additional marking steps and can directly reflect real-time process characteristics, helping to avoid material expansion or surface quality degradation caused by overheating.

[0003] Existing infrared imaging technology is mainly used for temperature detection of static targets. It lacks a systematic solution to deal with the spatiotemporal changes of thermal radiation texture and noise interference in dynamic cutting environments, which limits its effective application in optimizing copper tube cutting accuracy and reliability.

[0004] When the thermal radiation texture generated by local heating during the copper tube cutting process is used as visual guidance information, the randomness and instantaneousness of the thermal radiation texture make it difficult for the visual system to stably extract effective features, thus affecting the reliability of cutting path optimization. Specifically, in the visual guidance process based on thermal radiation texture, the randomness and instantaneousness of the texture and its confusion effect with the environmental thermal noise interfere with feature extraction. The generation of thermal radiation texture is affected by factors such as laser power fluctuations, copper tube wall thickness deviations and auxiliary airflow disturbances, and presents complex dynamic change characteristics. Summary of the invention

[0005] In order to overcome the above-mentioned defects of the prior art, the present invention provides a method and system for automatic copper tube cutting based on vision guidance, which finally realizes adaptive cutting of copper tubes through thermal radiation texture acquisition and feature extraction, signal separation and enhancement, and thermal stress modeling and correction, so as to solve the problem raised in the above-mentioned background technology that when the thermal radiation texture generated by local heating in the copper tube cutting process is used as visual guidance information, the randomness and instantaneousness of the thermal radiation texture make it difficult for the visual system to stably extract effective features, thereby affecting the reliability of cutting path optimization.

[0006] To achieve the above object, the present invention provides the following technical solution: a method for automatic copper tube cutting based on vision guidance, comprising the following steps: Step 1: Thermal radiation texture acquisition and feature extraction: The original thermal radiation texture image of the copper tube cutting area is acquired in real time by a high frame rate infrared camera, and the environmental parameters of the cutting process are recorded synchronously; the spatial frequency distribution of the original thermal radiation texture image is analyzed by wavelet transform technology, and the area of ​​concentrated thermal stress and the edge position of the high temperature gradient are marked; combined with the optical flow algorithm, the dynamic change vector of the thermal radiation texture is calculated, and the evolution trend of the thermal radiation texture over time is quantified to obtain the thermal radiation texture feature data set of the thermal radiation texture, including the spatial frequency map, the dynamic change vector field and the corresponding environmental parameter table; Explanation: Ensuring texture consistency through cross-stage correction means using cross-stage correction technology (such as dynamic time warping algorithm) to process the thermal radiation texture feature data set, adjust the texture morphology differences caused by heat accumulation or diffusion in different cutting stages (such as initial heating, mid-stage cutting, and late cooling), and ensure that the feature data set remains consistent and stable throughout the cutting process, thereby providing reliable basic data for subsequent signal enhancement and thermal stress modeling; Step 2: Signal separation and enhancement: Perform image segmentation and signal enhancement processing on the original thermal radiation texture image. Based on the thermal radiation texture feature dataset, use image segmentation to extract effective thermal radiation texture signals. Improve the clarity and continuity of the thermal radiation texture image through signal enhancement processing, and strengthen the prominence of the thermal stress distribution characteristics near the cutting line. In the image segmentation process, use the spatial frequency map as the weight to distinguish the high stress area and the low correlation noise area in the thermal radiation texture. Use the generative adversarial network to enhance the clarity and continuity, generate an enhanced image sequence, extract texture features, and mark the confidence score of each texture feature. Step 3: Thermal stress modeling and correction: Based on the enhanced image sequence and combined with the material properties of the copper tube, a thermal stress distribution model of the copper tube is constructed, and the temperature field and stress field during the cutting process are estimated using the finite element analysis method, where the temperature field is calculated using the heat conduction equation, and the stress field is derived based on the strain caused by thermal expansion; the thermal stress distribution map of the copper tube cutting process is generated and updated in real time, the boundaries of the cutting guide area are marked based on the thermal stress distribution map, and the dynamic threshold of the guide path is adjusted to ensure cutting accuracy, and the real-time updated thermal stress distribution map is output, and the boundary coordinates of the cutting guide area boundary and the adjustment log of the dynamic threshold are marked; Step 4: Implement adaptive cutting of copper tubes: Use Bezier curve algorithm to generate adaptive cutting path and execute it, adjust the log to optimize cutting parameters according to dynamic threshold, and generate a cutting report containing path coordinates, thermal radiation texture features and optimization parameters.

[0007] Preferably, the step 1 includes a thermal radiation texture cross-stage correction step: The time series of the thermal radiation texture feature data set is clustered by the dynamic time warping algorithm to analyze the texture morphology evolution trend at different cutting stages. Based on the clustering results, the feature alignment technology is used to adjust the dynamically changing vector field so that the texture features across stages remain consistent, and a corrected thermal radiation texture feature dataset is generated and passed to the signal separation and enhancement step.

[0008] Preferably, the step one includes an adaptive frame rate adjustment step, which adjusts the sampling frame rate of the infrared camera in real time according to the dynamic change speed of the thermal radiation texture or the environmental parameters of the cutting process to balance data quality and processing efficiency.

[0009] Preferably, the confidence score S of the texture feature is obtained as follows: Get the instantaneous feature vector v_t, record the average vector of the feature in the historical time series as v_avg, and use the formula The feature temporal consistency index C is calculated, where T is the time window; the feature temporal consistency index C represents the stability of the texture feature in the time series; The probability P of each texture feature in the discriminator is extracted, and combined with the consistency index C of the feature in the dynamically changing vector field, the confidence score S is calculated by the following formula: ; Among them, P is the probability value predicted by the discriminator, and α is the adjustment coefficient, which controls the impact of feature temporal consistency on the confidence score.

[0010] Preferably, in the process of acquiring the thermal stress distribution map, the cutting process environmental parameters are used to calibrate the copper tube thermal stress distribution model parameters, the enhanced image sequence is used as the initial condition input into the calibrated copper tube thermal stress distribution model, and the real-time updated thermal stress distribution map is output through iterative calculation to reflect the temperature gradient and stress concentration area on the surface of the copper tube.

[0011] Preferably, the step three includes a multi-scale thermal stress coupling step: based on the enhanced image sequence, a multi-resolution decomposition technique is used to separate the microscopic and macroscopic thermal effect features; a multi-scale copper tube thermal stress distribution model is constructed in combination with the microscopic defect distribution data of the copper tube material; a data fusion algorithm is used to integrate the microscopic stress field and the macroscopic stress field to generate a coupled thermal stress distribution map, thereby improving the accuracy of the cutting guide area boundary.

[0012] Preferably, the method further includes an airflow noise management step to solve the problem of thermal noise signal interference caused by the auxiliary airflow and distinguish between pseudo texture and real thermal radiation texture. Real-time monitoring is started during the cutting process. When the auxiliary airflow acts on the surface of the copper tube, the airflow noise management step is triggered, including: Step S11, monitoring auxiliary airflow parameters and predicting noise characteristics: recording the airflow parameters of the auxiliary airflow, including the pressure and flow rate parameters of the auxiliary airflow; establishing a mapping relationship between airflow noise and image features to obtain a pseudo-texture prediction model, which is used to output the brightness and spectral characteristics of the pseudo-texture; Step S12, extracting and analyzing the spatiotemporal characteristics of texture: obtaining an infrared image sequence and a pseudo-texture prediction result, using a 3D convolutional neural network to analyze the spatiotemporal characteristics of the infrared image, generating a spatiotemporal feature map, based on the regular characteristics of the real thermal radiation texture, suppressing the random interference of the pseudo-texture; Step S13, enhancing real texture features and marking confidence: processing texture data in the spatiotemporal feature map, using the attention mechanism to enhance the brightness and spectral characteristics of the real thermal radiation texture; combining the discriminator probability and feature temporal consistency, marking the confidence score for each texture feature.

[0013] Preferably, the dynamic threshold is obtained in the following manner: The enhanced image sequence is compared with the prediction results of the copper tube thermal stress distribution model to calculate the dynamic threshold of the thermal stress concentration area. The specific method is as follows: The boundary with the largest temperature gradient in the enhanced image is extracted, spatially matched with the stress concentration area predicted by the thermal stress distribution model of the copper tube, and the matching degree D is calculated; Based on the matching results, the dynamic threshold formula is defined as ,in is the reference temperature, γ is the gain coefficient, and H is the spatial complexity of the texture feature; γ is adjusted according to the texture feature confidence score S, and γ is positively correlated with the confidence score S, ensuring that high-confidence features have a greater impact on the threshold; The time trend of the image sequence is enhanced by historical time series, and the Kalman filter is used to correct the instantaneous fluctuation, remove outliers, and generate a smoothed dynamic threshold sequence; the instantaneous random fluctuation of the thermal radiation texture is corrected by time series analysis, and outliers are removed.

[0014] Preferably, the matching degree is calculated using the morphological evolution of the thermal stress concentration area, and the dynamic threshold is calculated as follows: ; ; in, is the second-order gradient of the image at time t, is the second-order gradient of the image at the initial moment, is the probability distribution of each frequency component in the spatial frequency diagram, and T is the time window.

[0015] To achieve the above object, the present invention provides the following technical solution: a copper tube automatic cutting system based on vision guidance, comprising: The thermal pattern acquisition module uses a high-frame-rate infrared camera to collect the original thermal radiation texture image of the copper tube cutting area in real time, and simultaneously records the environmental parameters of the cutting process; The feature extraction module uses wavelet transform technology to analyze the spatial frequency distribution and mark the thermal stress concentration area and the high temperature gradient edge. It combines the optical flow algorithm to calculate the dynamic change vector of the thermal radiation texture, quantify the evolution trend of the thermal radiation texture over time, capture the instantaneous and random characteristics, and generate a thermal radiation texture feature data set, including a spatial frequency map, a dynamic change vector field, and an environmental parameter table. The signal enhancement module performs image segmentation on the original thermal radiation texture image based on the thermal radiation texture feature dataset and extracts the effective thermal radiation texture signal; enhances the image clarity and continuity through the generative adversarial network, generates an enhanced image sequence, extracts texture features and annotates the confidence score for each feature; The stress modeling module receives the enhanced image sequence, combines the copper tube material properties, builds the copper tube thermal stress distribution model, generates and updates the thermal stress distribution map in real time; marks the cutting guide area boundary based on the thermal stress distribution map, and adjusts the dynamic threshold to ensure cutting accuracy; outputs the real-time updated thermal stress distribution map, cutting guide area boundary coordinates and dynamic threshold adjustment log; The path optimization module uses the Bezier curve algorithm to generate an adaptive cutting path based on the thermal stress distribution map, the boundary coordinates of the cutting guide area and the dynamic threshold adjustment log; optimizes the cutting parameters in combination with the dynamic threshold adjustment log, executes the cutting operation and generates a cutting report.

[0016] Technical effects and advantages of the present invention: The automatic copper tube cutting method based on vision guidance provided by the present invention can effectively detect and identify the thermal stress distribution in the copper tube cutting process by real-time acquisition of thermal radiation images and detailed analysis of the dynamic changes of thermal radiation textures using wavelet transform and optical flow algorithm; the thermal radiation texture images are processed and enhanced using enhanced generative adversarial networks to make the thermal stress distribution characteristics near the cutting line more obvious, so as to achieve refined cutting; and the copper tube thermal stress distribution model of the copper tube is constructed, and combined with the optimization and adjustment of the dynamic cutting path, the cutting parameters can be dynamically adjusted according to the changes in thermal stress during the actual cutting process to improve the cutting accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 The present invention is a flow chart of the automatic copper tube cutting method.

[0018] Figure 2 This is a flow chart of airflow noise management according to the present invention.

[0019] Figure 3 This is a structural block diagram of the copper tube automatic cutting system of the present invention. DETAILED DESCRIPTION

[0020] The exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided to enable a more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art.

[0021] At the same time, it should be understood that for the convenience of description, the sizes of the various parts shown in the drawings are not drawn according to the actual proportional relationship.

[0022] The following description of at least one exemplary embodiment is merely illustrative in nature and is in no way intended to limit the present application, its application, or uses.

[0023] Technologies, methods, and equipment known to ordinary technicians in the relevant art may not be discussed in detail, but where appropriate, the technologies, methods, and equipment should be considered as part of the specification.

[0024] Example 1, see Figure 1 The present invention provides a flow chart of a copper tube automatic cutting method. Figure 1 The method for automatic copper tube cutting based on vision guidance shown in the figure comprises the following steps: Step 1: Thermal radiation texture acquisition and feature extraction: The original thermal radiation texture image of the copper tube cutting area is acquired in real time by a high frame rate infrared camera, and the environmental parameters of the cutting process (such as laser power, cutting speed and auxiliary airflow pressure) are recorded synchronously; the spatial frequency distribution of the original thermal radiation texture image is analyzed by wavelet transform technology, and the area where thermal stress is concentrated and the edge position of the high temperature gradient are marked; combined with the optical flow algorithm, the dynamic change vector of the thermal radiation texture is calculated, and the evolution trend of the thermal radiation texture over time is quantified, thereby capturing the instantaneous and random characteristics of the thermal radiation texture, and obtaining the thermal radiation texture feature data set of the thermal radiation texture, including the spatial frequency map, the dynamic change vector field and the corresponding environmental parameter table; Step 2: Signal separation and enhancement: Perform image segmentation and signal enhancement processing on the original thermal radiation texture image. Based on the thermal radiation texture feature dataset, use image segmentation to extract effective thermal radiation texture signals. Improve the clarity and continuity of the thermal radiation texture image through signal enhancement processing, and strengthen the prominence of the thermal stress distribution characteristics near the cutting line. In the image segmentation process, use the spatial frequency map as the weight to distinguish the high stress area and the low correlation noise area in the thermal radiation texture. Use the generative adversarial network to enhance the clarity and continuity, generate an enhanced image sequence, extract texture features, and mark the confidence score of each texture feature. Step 3: Thermal stress modeling and correction: Generate and update the thermal stress distribution map in the copper tube cutting process in real time, mark the boundary of the cutting guide area based on the thermal stress distribution map, and adjust the dynamic threshold of the guide path to ensure the cutting accuracy, output the real-time updated thermal stress distribution map, and mark the boundary coordinates of the cutting guide area boundary and the adjustment log of the dynamic threshold; Explanation: Cutting guidance based on dynamic thresholds; Step 4: Implement adaptive cutting of copper tubes: Use Bezier curve algorithm to generate adaptive cutting path and execute it, adjust the log to optimize cutting parameters according to dynamic threshold, and generate a cutting report containing path coordinates, thermal radiation texture features and optimization parameters.

[0025] Background description: During the copper tube cutting process, the thermal radiation texture changes significantly with the movement of the laser and the accumulation of heat. For example, the texture is a uniform strip (temperature gradient 100℃ / mm) in the initial stage, and becomes an irregular patch (gradient drops to 50℃ / mm) due to thermal diffusion in the middle and late stages. The feature extraction in step one does not design a consistency correction mechanism for this cross-stage morphological evolution, which may cause subsequent signal enhancement and thermal stress modeling to be based on inconsistent feature inputs, affecting the cutting accuracy. Existing technologies mostly assume that texture features are relatively stable and do not pay attention to dynamic consistency issues. Based on this: In a possible embodiment, the step 1 includes a thermal radiation texture cross-stage correction step: The time series of the thermal radiation texture feature data set is clustered by the dynamic time warping algorithm to analyze the texture morphology evolution trend at different cutting stages. Based on the clustering results, the feature alignment technology is used to adjust the dynamically changing vector field to keep the texture features consistent across stages, generate a corrected thermal radiation texture feature dataset, and pass it to step 2 for signal separation and enhancement.

[0026] It is necessary to further explain in the embodiment of the present invention that the step 1 includes an adaptive frame rate adjustment step, which adjusts the sampling frame rate of the infrared camera in real time according to the dynamic change speed of the thermal radiation texture or the cutting process environmental parameters to balance the data quality and processing efficiency; including: The optical flow algorithm is used to calculate the dynamic change vector of the thermal radiation texture and quantify the instantaneous speed of texture change; Based on the pre-trained machine learning model, combined with the changing trends of different materials and process parameters, the frame rate under current conditions is predicted by analyzing historical cutting data and environmental parameters; According to the quantified texture change speed and the prediction results of the machine learning model, the sampling frame rate of the infrared camera is dynamically adjusted to ensure that the data processing efficiency is optimized while capturing instantaneous features.

[0027] In a possible embodiment, the sampling frame rate is adjusted according to the spatial frequency change rate of the thermal radiation texture and the nonlinear interaction of environmental parameters; the nonlinear interaction means that the environmental parameters are not a simple linear superposition relationship, but jointly affect the thermal radiation texture through complex physical mechanisms (such as heat conduction, convection, and radiation); the nonlinear interaction of environmental parameters is analyzed, and the impact on the texture frequency is predicted through a nonlinear regression model.

[0028] It needs to be further explained in the embodiment of the present invention that the confidence score S of the texture feature is obtained as follows: Get the instantaneous feature vector v_t, record the average vector of the feature in the historical time series (such as the first 5 frames) as v_avg, and use the formula The feature temporal consistency index C is calculated, where T is the time window (e.g., 0.5 seconds); the feature temporal consistency index C represents the stability of the texture feature in the time series; The probability P of each texture feature in the discriminator is extracted, and combined with the consistency index C of the feature in the dynamically changing vector field, the confidence score S is calculated by the following formula: ; Among them, P is the probability value predicted by the discriminator, and α is the adjustment coefficient, which controls the impact of feature temporal consistency on the confidence score (for example, the value range is 0.1 to 1.0). The formula uses an exponential function to reflect the nonlinear impact of feature temporal consistency on the confidence score, avoiding the simplification of the traditional linear weighted summation method, making the confidence score more responsive to dynamically changing feature points.

[0029] It needs to be further explained in the embodiment of the present invention that the thermal stress distribution map is obtained by: based on the enhanced image sequence output in step 2, combined with the material properties of the copper tube (including thermal conductivity, thermal expansion coefficient, density and specific heat capacity, etc.), a thermal stress distribution model of the copper tube is constructed, and the temperature field and stress field in the cutting process are estimated by the finite element analysis method, wherein the temperature field is calculated by the heat conduction equation, and the stress field is derived based on the strain caused by thermal expansion; The cutting process environmental parameters (such as laser power 2000W, cutting speed 10mm / s, auxiliary airflow pressure 5bar) are used to calibrate the parameters of the copper tube thermal stress distribution model (such as heat input power and heat dissipation coefficient in boundary conditions, laser power determines the heat input amount, and airflow pressure affects the heat dissipation rate); the enhanced image sequence is input as the initial condition into the calibrated copper tube thermal stress distribution model, and the real-time updated thermal stress distribution map is output through iterative calculation to reflect the temperature gradient and stress concentration area on the surface of the copper tube.

[0030] Background description: The thermal stress distribution model of copper tubes is based on enhanced image sequences and material properties, using finite element analysis, but does not consider the multi-scale coupling of microscopic (such as material grain boundary defects, size 1-10μm) and macroscopic (such as overall heat diffusion, size 1-10mm) thermal effects. For example, microscopic defects may amplify local stress (local stress increases to 80MPa), affecting the accuracy of the macroscopic distribution map. Existing technologies are mostly based on single-scale modeling, and do not solve the problem of multi-scale interaction. Based on this: In a possible embodiment, the step three includes a multi-scale thermal stress coupling step: based on the enhanced image sequence, a multi-resolution decomposition technique (such as pyramid transformation) is used to separate microscopic and macroscopic thermal effect features; Combined with the microscopic defect distribution data of copper tube materials (pre-acquired through ultrasonic testing), a multi-scale copper tube thermal stress distribution model is constructed; The data fusion algorithm (such as weighted least squares method) is used to integrate the micro stress field (local features) and the macro stress field to generate a coupled thermal stress distribution map and improve the accuracy of the cutting guide area boundary.

[0031] It needs to be further explained in the embodiment of the present invention that the multi-scale thermal stress coupling step includes: Microscopic feature extraction: Based on the enhanced image sequence, the wavelet packet decomposition technology is used to separate the microscopic thermal effect features, extract the local temperature gradient changes with a scale less than 10μm, and combine the microscopic defect distribution data of the copper tube material to generate the microscopic thermal effect feature map; Macro feature calculation: Through two-dimensional Fourier transform analysis, the image sequence is enhanced, the macro thermal diffusion pattern with a scale greater than 1 mm is extracted, and the macro thermal effect feature map is generated; Multi-scale fusion: Use adaptive weighted fusion algorithm to integrate microscopic thermal effect feature map and macroscopic thermal effect feature map, and define fusion weights ,in, is the microscopic temperature gradient, is the macroscopic temperature gradient, λ is the adjustment coefficient (value range 0.1-0.5); The coupled thermal stress distribution map is generated through iterative optimization to ensure that the boundary coordinate accuracy error is less than 0.1 mm.

[0032] It needs to be further explained in the embodiment of the present invention that the multi-scale thermal stress coupling step includes: Multi-scale feature separation: Based on the enhanced image sequence, the variational mode decomposition technology is used to separate the microscopic thermal effect features (frequency range 10-100Hz) and the macroscopic thermal effect features (frequency range 0.1-1Hz), and the corresponding microscopic feature maps and macroscopic feature maps are generated; Quantification of defect impact: Combined with the microscopic defect distribution data of copper tube materials, the local stress amplification factor Calculate the micro stress correction, where d is the defect size (μm), D is the copper tube wall thickness (mm), is the material correlation coefficient (value range is 0.5-2); Dynamic coupling calculation: Use deep belief networks to fuse micro-feature maps and macro-feature maps, train the model to predict the dynamic impact of defects on thermal stress distribution, and generate a real-time updated coupled thermal stress distribution map; adjust the cutting guide area boundary according to the prediction results to ensure that the deviation between the boundary coordinates and the actual stress concentration area is less than 0.15mm.

[0033] Background description: The air refractive index disturbance or environmental heat dissipation caused by the auxiliary airflow will superimpose thermal noise signals in the image, which are highly similar to the real thermal radiation texture in brightness and spectral characteristics, causing the system to misjudge the thermal stress concentration area, thereby causing the cutting path to deviate from the target position. In order to solve the problem that the pseudo-texture caused by the auxiliary airflow is difficult to identify and filter out: It is necessary to further explain in the embodiment of the present invention that the step 2 also includes an airflow noise management step to solve the problem of thermal noise signal interference caused by the auxiliary airflow and distinguish the problem of pseudo texture and real thermal radiation texture. Real-time monitoring is started during the cutting process. When the auxiliary airflow acts on the surface of the copper tube, the airflow noise management step is triggered. Figure 2 The airflow noise management flow chart includes: Step S11, monitoring auxiliary airflow parameters and predicting noise characteristics: recording the airflow parameters of the auxiliary airflow, including the pressure and flow rate parameters of the auxiliary airflow; establishing a mapping relationship between airflow noise and image features to obtain a pseudo-texture prediction model, which is used to output the brightness and spectrum characteristics of the pseudo-texture as a reference for subsequent filtering; Step S12, extracting and analyzing the spatiotemporal features of texture: obtaining an infrared image sequence and a pseudo-texture prediction result, using a 3D convolutional neural network to analyze the spatiotemporal features of the infrared image (for example, the real thermal radiation texture should remain consistent in multiple time frames, while the randomness of airflow noise may fluctuate over time), generating a spatiotemporal feature map, based on the regularity of the real thermal radiation texture, suppressing the random interference of the pseudo-texture; Step S13, enhancing the real texture features and marking the confidence: processing the texture data in the spatiotemporal feature map, using the attention mechanism to enhance the brightness and spectral characteristics of the real thermal radiation texture; combining the discriminator probability and the feature temporal consistency, marking the confidence score for each texture feature; Explanation: Suppose at a certain moment, the enhanced thermal radiation texture image shows an area with strong thermal stress concentration; through the Bayesian optimization algorithm, according to the characteristics and confidence score of the image, the system will dynamically adjust the threshold of the cutting path; if the thermal radiation texture of a certain area is very clear and reliable, the threshold will be lowered accordingly to accurately cut the area; if the thermal radiation texture is relatively fuzzy, the system will increase the threshold to avoid incorrect cutting.

[0034] It needs to be further explained in the embodiment of the present invention that the dynamic threshold is obtained in the following manner: The enhanced image sequence is compared with the prediction results of the copper tube thermal stress distribution model to calculate the dynamic threshold of the thermal stress concentration area. The specific method is as follows: Extract the boundary with the largest temperature gradient in the enhanced image (such as the area with gradient ≥ 200℃ / mm), perform spatial matching with the stress concentration area predicted by the thermal stress distribution model of the copper tube (such as stress ≥ 50MPa), and calculate the matching degree (for example, use cosine similarity to quantify the spatial consistency between the image and the model, and regard the cosine similarity as the matching degree D. When the matching degree is high, close to 1, the enhanced image is highly consistent with the model, and the threshold increase is large; when the matching degree D is low, the threshold is conservative to reduce misjudgment); Based on the matching results, the dynamic threshold formula is defined as ,in is the reference temperature, γ is the gain coefficient, and H is the spatial complexity of the texture feature; γ is adjusted according to the texture feature confidence score S, and γ is positively correlated with the confidence score S, ensuring that high-confidence features have a greater impact on the threshold; In a possible embodiment, the time trend of the image sequence is enhanced through historical time series (such as the previous 10 frames), and Kalman filtering is used to correct instantaneous fluctuations, and outliers (such as sudden temperature changes of ±25°C) are eliminated to generate a smoothed dynamic threshold sequence; through time series analysis (based on the texture trend of the previous 10 frames of images, using exponential smoothing method α=0.3), the instantaneous random fluctuations of the thermal radiation texture are corrected, and outliers are eliminated to ensure that the dynamic threshold reflects the stable thermal stress distribution characteristics.

[0035] In a possible embodiment, the morphological evolution of the thermal stress concentration area is used Indicates the matching degree, and the dynamic threshold is calculated as follows: ; ; in, is the reference temperature (calculated based on the median of the local temperature of the enhanced image), is the gain coefficient, is the second-order gradient of the image at time t, is the second-order gradient of the image at the initial moment, is the spatial complexity of texture features, is the probability distribution of each frequency component in the spatial frequency graph (similar to Shannon entropy); in this formula, the gradient change It represents the degree of change of the texture structure in the image and reflects the morphological evolution of the thermal stress concentration area during the cutting process. The integral term captures the evolution of the texture over time and improves the responsiveness of the dynamic threshold to the change of thermal stress during the cutting process. Combined with the Kalman filter for time smoothing of the threshold, outliers are further removed to ensure the stability and accuracy of the dynamic threshold.

[0036] Example 2, see Figure 3 The structure block diagram of the copper tube automatic cutting system is shown in FIG. 1 . The embodiment of the present invention provides a copper tube automatic cutting system based on visual guidance, comprising: The thermal pattern acquisition module uses a high-frame-rate infrared camera to collect the original thermal radiation texture image of the copper tube cutting area in real time, and simultaneously records the environmental parameters of the cutting process (such as laser power, cutting speed, and auxiliary airflow pressure); The feature extraction module uses wavelet transform technology to analyze the spatial frequency distribution and mark the thermal stress concentration area and the high temperature gradient edge. It combines the optical flow algorithm to calculate the dynamic change vector of the thermal radiation texture, quantify the evolution trend of the thermal radiation texture over time, capture the instantaneous and random characteristics, and generate a thermal radiation texture feature data set, including a spatial frequency map, a dynamic change vector field, and an environmental parameter table. The signal enhancement module performs image segmentation on the original thermal radiation texture image based on the thermal radiation texture feature dataset and extracts the effective thermal radiation texture signal; enhances the image clarity and continuity through the generative adversarial network, generates an enhanced image sequence, extracts texture features and annotates the confidence score for each feature; The stress modeling module receives the enhanced image sequence, combines the copper tube material properties (thermal conductivity, thermal expansion coefficient, etc.), builds the copper tube thermal stress distribution model, generates and updates the thermal stress distribution map in real time; marks the cutting guide area boundary based on the thermal stress distribution map, and adjusts the dynamic threshold to ensure cutting accuracy; outputs the real-time updated thermal stress distribution map, cutting guide area boundary coordinates and dynamic threshold adjustment log; The path optimization module uses the Bezier curve algorithm to generate an adaptive cutting path based on the thermal stress distribution map, the boundary coordinates of the cutting guide area and the dynamic threshold adjustment log. It optimizes the cutting parameters (such as laser power or airflow pressure) in combination with the dynamic threshold adjustment log, executes the cutting operation and generates a cutting report.

[0037] What needs to be further explained in the embodiment of the present invention is that the thermal pattern acquisition module includes an adaptive frame rate adjustment unit, which adjusts the sampling frame rate of the infrared camera in real time according to the dynamic change speed of the thermal radiation texture or the environmental parameters of the cutting process to balance data quality and processing efficiency.

[0038] What needs to be further explained in the embodiment of the present invention is that the feature extraction module includes a thermal radiation texture cross-stage correction unit, which clusters the time series of the thermal radiation texture feature data set through a dynamic time warping algorithm to analyze the texture morphology evolution trend at different cutting stages; Based on the clustering results, the feature alignment technology is used to adjust the dynamically changing vector field so that the texture features across stages remain consistent. The corrected thermal radiation texture feature dataset is generated and passed to the signal enhancement module.

[0039] It needs to be further explained in the embodiment of the present invention that the signal enhancement module includes an airflow noise management unit to solve the problem of thermal noise signal interference caused by the auxiliary airflow and distinguish between pseudo texture and real thermal radiation texture. Real-time monitoring is started during the cutting process. When the auxiliary airflow acts on the surface of the copper tube, the airflow noise management unit is triggered, including: Step S11, monitoring auxiliary airflow parameters and predicting noise characteristics: recording the airflow parameters of the auxiliary airflow, including the pressure and flow rate parameters of the auxiliary airflow; establishing a mapping relationship between airflow noise and image features to obtain a pseudo-texture prediction model, which is used to output the brightness and spectral characteristics of the pseudo-texture; Step S12, extracting and analyzing the spatiotemporal characteristics of texture: obtaining an infrared image sequence and a pseudo-texture prediction result, using a 3D convolutional neural network to analyze the spatiotemporal characteristics of the infrared image, generating a spatiotemporal feature map, based on the regular characteristics of the real thermal radiation texture, suppressing the random interference of the pseudo-texture; Step S13, enhancing real texture features and marking confidence: processing texture data in the spatiotemporal feature map, and using an attention mechanism to enhance the brightness and spectral characteristics of the real thermal radiation texture.

[0040] What needs to be further explained in the embodiments of the present invention is that the stress modeling module includes a multi-scale thermal stress coupling unit, which uses multi-resolution decomposition technology to separate micro and macro thermal effect characteristics based on enhanced image sequences; combines the micro defect distribution data of copper tube materials to construct a multi-scale copper tube thermal stress distribution model; uses a data fusion algorithm to integrate the micro stress field and the macro stress field to generate a coupled thermal stress distribution map, thereby improving the accuracy of the cutting guide area boundary.

[0041] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for automatic copper tube cutting based on vision guidance, characterized in that: The following steps are involved: Step 1: Thermal radiation texture acquisition and feature extraction: The original thermal radiation texture image of the copper tube cutting area is collected by infrared camera, and the environmental parameters are recorded synchronously. The thermal radiation texture feature data set is extracted and the texture consistency is ensured through cross-stage correction; the thermal radiation texture feature data set includes spatial frequency map, dynamic change vector field and corresponding environmental parameter table; Step 2: Signal separation and enhancement: Separate and enhance the thermal radiation texture signal based on the thermal radiation texture feature dataset, generate an enhanced image sequence and annotate the confidence score of each texture feature; Step 3: Thermal stress modeling and correction: Based on the enhanced image sequence and material properties, a multi-scale coupled thermal stress distribution model of the copper tube is constructed. The finite element analysis method is used to estimate the temperature field and stress field during the cutting process. The thermal stress distribution map is generated and updated in real time. The dynamic threshold is calculated based on the morphological evolution to guide the cutting path, and the boundary coordinates and adjustment log are output. Step 4: Adaptive cutting execution: Use the Bezier curve algorithm to generate an adaptive cutting path and execute it, adjust the log to optimize the cutting parameters according to the dynamic threshold, and generate a cutting report containing path coordinates, thermal radiation texture features and optimization parameters.

2. The method for automatic copper tube cutting based on vision guidance according to claim 1 is characterized in that: The step 1 includes a thermal radiation texture cross-stage correction step: The time series of the thermal radiation texture feature data set is clustered by the dynamic time warping algorithm to analyze the texture morphology evolution trend at different cutting stages. Based on the clustering results, the feature alignment technology is used to adjust the dynamically changing vector field so that the texture features across stages remain consistent, and a corrected thermal radiation texture feature dataset is generated and passed to the signal separation and enhancement step.

3. The method for automatic copper tube cutting based on vision guidance according to claim 1 is characterized in that: The step one includes an adaptive frame rate adjustment step, which adjusts the sampling frame rate of the infrared camera in real time according to the dynamic change speed of the thermal radiation texture or the environmental parameters of the cutting process to balance the data quality and processing efficiency.

4. The method for automatic copper tube cutting based on vision guidance according to claim 1 is characterized in that: The confidence score S of the texture feature is obtained as follows: Get the instantaneous feature vector v_t, record the average vector of the feature in the historical time series as v_avg, and use the formula The feature temporal consistency index C is calculated, where T is the time window; the feature temporal consistency index C represents the stability of the texture feature in the time series; The probability P of each texture feature in the discriminator is extracted, and combined with the consistency index C of the feature in the dynamically changing vector field, the confidence score S is calculated by the following formula: ； Among them, P is the probability value predicted by the discriminator, and α is the adjustment coefficient, which controls the impact of feature temporal consistency on the confidence score.

5. The method for automatic copper tube cutting based on vision guidance according to claim 1 is characterized in that: In the process of acquiring the thermal stress distribution map, the cutting process environmental parameters are used to calibrate the parameters of the copper tube thermal stress distribution model. The enhanced image sequence is used as the initial condition to input the calibrated copper tube thermal stress distribution model. The real-time updated thermal stress distribution map is output through iterative calculation to reflect the temperature gradient and stress concentration area on the surface of the copper tube.

6. The method for automatic copper tube cutting based on vision guidance according to claim 1 is characterized in that: The step three includes a multi-scale thermal stress coupling step: based on the enhanced image sequence, a multi-resolution decomposition technology is used to separate the microscopic and macroscopic thermal effect characteristics; a multi-scale copper tube thermal stress distribution model is constructed in combination with the microscopic defect distribution data of the copper tube material; a data fusion algorithm is used to integrate the microscopic stress field and the macroscopic stress field to generate a coupled thermal stress distribution map, thereby improving the accuracy of the cutting guide area boundary.

7. The method for automatic copper tube cutting based on vision guidance according to claim 1 is characterized in that: It also includes an airflow noise management step, which starts real-time monitoring during the cutting process. When the auxiliary airflow acts on the surface of the copper tube, the airflow noise management step is triggered, including: Step S11, monitoring auxiliary airflow parameters and predicting noise characteristics: recording the airflow parameters of the auxiliary airflow, including the pressure and flow rate parameters of the auxiliary airflow; establishing a mapping relationship between airflow noise and image features to obtain a pseudo-texture prediction model, which is used to output the brightness and spectral characteristics of the pseudo-texture; Step S12, extracting and analyzing the spatiotemporal characteristics of texture: obtaining an infrared image sequence and a pseudo-texture prediction result, using a 3D convolutional neural network to analyze the spatiotemporal characteristics of the infrared image, generating a spatiotemporal feature map, based on the regular characteristics of the real thermal radiation texture, suppressing the random interference of the pseudo-texture; Step S13, enhancing real texture features and marking confidence: processing texture data in the spatiotemporal feature map, and using an attention mechanism to enhance the brightness and spectral characteristics of the real thermal radiation texture.

8. A method for automatic copper tube cutting based on vision guidance according to any one of claims 1 to 7, characterized in that: The dynamic threshold is obtained as follows: The enhanced image sequence is compared with the prediction results of the copper tube thermal stress distribution model to calculate the dynamic threshold of the thermal stress concentration area. The specific method is as follows: The boundary with the largest temperature gradient in the enhanced image is extracted, spatially matched with the stress concentration area predicted by the thermal stress distribution model of the copper tube, and the matching degree D is calculated; Based on the matching results, the dynamic threshold formula is defined as ,in is the reference temperature, γ is the gain coefficient, and H is the spatial complexity of the texture feature; γ is adjusted according to the texture feature confidence score S, and γ is positively correlated with the confidence score S; The time trend of the image sequence is enhanced by historical time series, and the Kalman filter is used to correct the instantaneous fluctuation, remove outliers, and generate a smoothed dynamic threshold sequence; the instantaneous random fluctuation of the thermal radiation texture is corrected by time series analysis, and outliers are removed.

9. The method for automatic copper tube cutting based on vision guidance according to claim 8, characterized in that: The matching degree is calculated using the morphological evolution of the thermal stress concentration area, and the dynamic threshold is calculated as follows: ； ； in, is the second-order gradient of the image at time t, is the second-order gradient of the image at the initial moment, is the probability distribution of each frequency component in the spatial frequency diagram, and T is the time window.

10. A copper tube automatic cutting system based on vision guidance, characterized in that: include: The thermal pattern acquisition module uses a high-frame-rate infrared camera to collect the original thermal radiation texture image of the copper tube cutting area in real time, and simultaneously records the environmental parameters of the cutting process; The feature extraction module uses wavelet transform technology to analyze the spatial frequency distribution and mark the areas of thermal stress concentration and the edges of high temperature gradients; Combined with the optical flow algorithm, the dynamic change vector of the thermal radiation texture is calculated, the evolution trend of the thermal radiation texture over time is quantified, the instantaneous and random characteristics are captured, and a thermal radiation texture feature data set is generated, including a spatial frequency map, a dynamic change vector field, and an environmental parameter table; The signal enhancement module performs image segmentation on the original thermal radiation texture image based on the thermal radiation texture feature dataset and extracts the effective thermal radiation texture signal; enhances the image clarity and continuity through the generative adversarial network, generates an enhanced image sequence, extracts texture features and annotates the confidence score for each feature; The stress modeling module receives the enhanced image sequence, combines the copper tube material properties, builds the copper tube thermal stress distribution model, and generates and updates the thermal stress distribution map in real time; Mark the cutting guide area boundary based on the thermal stress distribution diagram and adjust the dynamic threshold to ensure cutting accuracy; Output real-time updated thermal stress distribution map, cutting guide area boundary coordinates and dynamic threshold adjustment log; The path optimization module uses the Bezier curve algorithm to generate an adaptive cutting path based on the thermal stress distribution map, the boundary coordinates of the cutting guide area and the dynamic threshold adjustment log; optimizes the cutting parameters in combination with the dynamic threshold adjustment log, executes the cutting operation and generates a cutting report.

Images