Three-dimensional imaging detection system for high-temperature furnace tube based on electromagnetic ultrasonic and robot cooperation

Abstract

The application discloses a kind of high-temperature furnace tube three-dimensional imaging detection systems based on electromagnetic ultrasonic and robot cooperation, comprising: data acquisition and arrangement module, for obtaining and structured processing multidimensional aging data;Three-dimensional reconstruction module, for the digital modeling of furnace tube space structure;Color mapping module, for generating three-dimensional aging distribution image with color distinction;Abnormal labeling module, for automatically labeling abnormal aging area;Key position judging module, for judging whether abnormal area is located at key pressure-bearing position to generate warning mark;Visual optimization module, for adjusting display parameters to optimize image;Data transmission and decision interaction module, for integrating data and transmitting to automatic decision system to obtain feedback;Feedback update and storage module, for updating image mark and recording detection archives;Realize the accurate three-dimensional visualization and intelligent analysis of furnace tube aging state, help to discover potential risk in time, improve equipment safety and maintenance efficiency.

Description

Technical Field

[0001] This invention relates to the field of industrial inspection and information technology, and in particular to a three-dimensional imaging inspection system for high-temperature furnace tubes based on electromagnetic ultrasound and robot collaboration. Background Technology

[0002] In the field of industrial equipment maintenance, the inspection and aging assessment of high-temperature furnace tubes is a crucial research direction, directly impacting production safety and equipment lifespan. As a core component in high-temperature environments, the accurate assessment of the aging state of furnace tubes is irreplaceable for preventing sudden failures and ensuring production continuity. However, current research and application methods often face challenges when inspecting furnace tubes in complex environments, including insufficiently intuitive data presentation and difficulties in quickly understanding and utilizing assessment results. These methods typically present large amounts of inspection data in tabular or two-dimensional charts, lacking a three-dimensional representation of spatial distribution. This makes it difficult for operators to quickly grasp the full picture of the aging state and limits the efficiency of subsequent decision-making.

[0003] A deeper analysis of the challenges in this field reveals that the inadequacy of data visualization is the primary issue. Because test data typically involves multi-dimensional information, including aging degree and location distribution, a simple two-dimensional display cannot fully reflect the true state of the furnace tubes in three-dimensional space. This limitation of visualization methods further leads to another critical problem: operators and automated systems cannot intuitively obtain the full picture of aging distribution, thus affecting the speed of response to test results and accurate decision-making. These two problems are interconnected; the former directly causes the latter, significantly reducing the practicality and guidance of aging assessments.

[0004] Therefore, how to transform complex furnace tube aging data into intuitive three-dimensional images, and clearly display the aging degree of different areas through color coding and distribution maps, has become a key issue in improving the practicality and decision-making efficiency of the detection system. Summary of the Invention

[0005] This invention addresses the problems of insufficient visualization of aging data and low decision-making efficiency in existing technologies by providing a three-dimensional imaging detection system for high-temperature furnace tubes based on electromagnetic ultrasound and robot collaboration.

[0006] The high-temperature furnace tube three-dimensional imaging inspection system based on electromagnetic ultrasound and robot collaboration includes a data acquisition and processing module, a three-dimensional reconstruction module, a color mapping module, an anomaly annotation module, a key part judgment module, a visualization optimization module, a data transmission and decision interaction module, and a feedback update and storage module. The data acquisition and processing module is used to acquire multi-dimensional aging data from the high-temperature furnace tube testing equipment, classify and process the data according to the degree of material degradation and location information in different areas, and perform preliminary structuring processing on the data through preset classification rules to obtain the processed aging dataset. 3D Reconstruction Module: This module uses a 3D reconstruction algorithm to digitally model the spatial structure of the furnace tubes based on the processed aging dataset. It combines location information and aging degree data to map planar data onto a 3D spatial model, generating an initial 3D furnace tube model. Color mapping module: It is used to extract the aging degree values ​​of each region based on the initial three-dimensional furnace tube model, and to classify and identify different aging degrees through color mapping technology, generating a three-dimensional aging distribution image with color distinction. Anomaly labeling module: This module is used to analyze the distribution pattern of aging degree corresponding to color-coded 3D aging distribution images, and automatically label abnormal aging areas within a preset threshold range to obtain a labeled distribution image. Critical component judgment module: It is used to extract the spatial location information of abnormal aging areas from the labeled distribution image, and combine it with the overall structure data of the furnace tube to determine whether the abnormal area is located in a critical pressure-bearing part. If it is located in a critical part, a high-priority warning sign is generated. Visualization optimization module: Used to adjust the display parameters of the 3D aging distribution image based on high-priority warning signs, highlight the color contrast and spatial position of abnormal areas, optimize the image through dynamic rendering technology, and generate the final visualization result; Data transmission and decision interaction module: This module integrates aging distribution data and warning label information for the final visualization results, transmits them to the automated decision system through a data interface, obtains real-time analysis feedback on the aging status from the system, and determines subsequent processing instructions. Feedback update and storage module: It is used to update the dynamic label content in the three-dimensional aging distribution image based on real-time analysis feedback, synchronously adjust the display status of abnormal areas, and record the image data and feedback information of each update through the data storage module to obtain a complete detection archive.

[0007] As a further preferred embodiment of the high-temperature furnace tube three-dimensional imaging detection system based on electromagnetic ultrasound and robot collaboration of the present invention, the data acquisition and processing module specifically includes: Multi-dimensional aging data, including the degree of material degradation and location information, is obtained from high-temperature furnace tube testing equipment. Noise is removed by data cleaning methods to obtain cleaned aging data. Based on the aging data after cleaning, the degree and location information of material degradation are extracted, and the K-means clustering algorithm is used to preliminarily classify the data to obtain the classified data groups; Based on the categorized data groups, and combined with the preset categorization rules, the degree of material degradation and location information are matched to determine the degradation characteristics of each group; If the degradation characteristics of the group meet the preset threshold, the support vector machine algorithm is used to further quantify the degradation degree to obtain the quantified degradation degree value. Based on the quantified degradation level values ​​and location information, degradation distribution maps for each region are generated to determine the degradation distribution characteristics. By analyzing the degradation distribution characteristics, a decision tree algorithm is used to predict the degradation trend in different regions, thus obtaining the predicted aging trend. Based on the predicted aging trends, a structured aging dataset is generated by combining location information, which includes the degree of degradation and predicted trends of each region.

[0008] As a further preferred embodiment of the high-temperature furnace tube three-dimensional imaging detection system based on electromagnetic ultrasound and robot collaboration of the present invention, the three-dimensional reconstruction module specifically includes: For the sorted aging dataset, a three-dimensional reconstruction algorithm is used to digitize the furnace tube space, and the location information and aging degree data are integrated to generate a preliminary three-dimensional furnace tube model. Based on the preliminary three-dimensional furnace tube model, key areas in the spatial structure are extracted. Combined with location information, the aging degree distribution in the model is locally divided to obtain the regional distribution data after division. For the divided regional distribution data, the differences in aging degree of each region are obtained and compared using a preset threshold. If the aging degree of a certain region exceeds the threshold, the spatial structure of that region is refined to obtain refined regional structure data. Based on the refined regional structure data and combined with location information, the aging degree in three-dimensional space is labeled in layers to generate a three-dimensional furnace tube model with layered labels. For a three-dimensional furnace tube model with layered annotations, the aging degree and spatial structure features of each layer are extracted. The support vector machine algorithm is used to analyze the aging distribution pattern of different regions and determine the aging distribution characteristics of each region. Based on the aging distribution characteristics of each region and combined with the location information in three-dimensional space, the aging trend of the furnace tube space is compared by region to obtain the aging trend data of each region. Based on the aging trend data of different regions, spatial structure and location information are integrated, and the trend data is mapped onto the three-dimensional furnace tube model to generate the final three-dimensional model with trend annotations.

[0009] As a further preferred embodiment of the high-temperature furnace tube three-dimensional imaging detection system based on electromagnetic ultrasound and robot collaboration of the present invention, the color mapping module specifically includes: For the furnace tube structure in the 3D model, the aging degree information of each region is obtained, and the different aging degrees are graded and labeled by color mapping method to obtain a distribution view with color differentiation. Based on the color differentiation results in the distribution view, the aging distribution characteristics of each region are extracted and compared using a preset threshold. If the aging degree of a certain region exceeds the threshold, the structural characteristics of that region are analyzed in depth to determine the distribution of high-risk regions. Based on the distribution of high-risk areas, corresponding spatial data is obtained, and combined with furnace tube structure information, these areas are locally magnified to obtain a refined local view. Based on the refined local view, the aging distribution details of the local area are extracted. Combined with the area division information, the degree of aging is annotated in multiple layers to generate a local distribution view with hierarchical annotations. For a local distribution view with hierarchical labeling, the differences in aging degree at each level are obtained. The support vector machine algorithm is used to classify the difference data and determine the aging distribution pattern of each region. Based on the results of the aging distribution pattern, combined with spatial data and structural features, the aging distribution in the furnace tube structure is dynamically updated to generate an updated three-dimensional distribution view. For the updated 3D distribution view, the latest aging distribution information is obtained. Combined with the regional division and hierarchical labeling data, the view is optimized and adjusted to obtain the final 3D aging distribution view.

[0010] As a further preferred embodiment of the high-temperature furnace tube three-dimensional imaging detection system based on electromagnetic ultrasound and robot collaboration of the present invention, the anomaly annotation module specifically includes: By extracting data from 3D images with color distinctions, the aging degree information corresponding to the color labels is obtained. Image analysis technology is used to preliminarily classify the aging degree of each region, and the aging distribution data after classification is obtained. Based on the categorized aging distribution data and combined with the analysis method of distribution patterns, the distribution characteristics of aging degree in different regions are identified, and the changing trend of aging degree in each region is determined. Based on the trend of aging, the corresponding regional division information is obtained, and abnormal regions are compared with preset thresholds. If the aging of a certain region exceeds the preset threshold, it is marked as an abnormal region, and the marked region data is generated. Using the marked area data, anomalies are identified through automatic annotation technology, generating a distribution view with annotation information. Based on the distribution view with annotation information, the abnormal area features in the annotation results are extracted, and combined with the spatial information of the 3D image, the abnormal area is locally augmented to obtain the augmented view data. Based on the enhanced view data, and combined with region division and color identification information, the distribution view is subjected to multi-level rendering processing to generate the final labeled distribution view; By using the final labeled distribution view, the distribution pattern data of aging degree is obtained. The distribution characteristics of abnormal areas are classified by combining the support vector machine algorithm to determine the aging distribution pattern of each area.

[0011] As a further preferred embodiment of the high-temperature furnace tube three-dimensional imaging detection system based on electromagnetic ultrasound and robot collaboration of the present invention, the key component judgment module specifically includes: Spatial coordinate data of abnormal aging regions are extracted from the labeled distribution image. Image segmentation technology is used to divide the boundaries of the abnormal regions to obtain a coordinate dataset with clear boundaries. Based on a well-defined coordinate dataset and a pre-established furnace tube structure model, the spatial coordinates of the abnormal region are mapped to the structure model to determine the location distribution of the abnormal region in the furnace tube. By using location distribution data, the geometric features of the pressure-bearing parts in the furnace tube structure model are obtained. If the coordinate data of the abnormal area overlaps with the geometric features of the pressure-bearing parts, the abnormal area is determined to be located in the pressure-bearing parts, and the pressure-bearing area judgment result is obtained. Based on the assessment results of the pressure-bearing area, and combined with the pre-set list of key parts, if the pressure-bearing area matches the location in the list of key parts, high-priority warning label data is generated. The spatial location and priority information of the high-priority warning signs are extracted from the data. The abnormal areas are highlighted with color in the visualization view of the furnace tube structure model using rendering technology to obtain the highlighted visualization view. Based on the labeled visualization view, a dataset of distribution features of abnormal regions is generated. The k-means clustering algorithm is used to classify the distribution patterns of abnormal regions, and the classified distribution pattern data is obtained. By combining the categorized distribution pattern data with the geometric information of the furnace tube structure model, a spatial distribution statistical table of abnormal areas is generated to determine the distribution pattern of abnormal areas.

[0012] As a further preferred embodiment of the high-temperature furnace tube three-dimensional imaging detection system based on electromagnetic ultrasound and robot collaboration of the present invention, the visualization optimization module specifically includes: Obtain the identification data of the abnormal area from the high-priority warning signs, extract the spatial coordinates and priority information corresponding to the signs, and obtain the coordinate dataset of the abnormal area. Based on the coordinate dataset of the abnormal region, the current display parameters of the three-dimensional aging distribution image are obtained, and the color contrast is adjusted using a parameter mapping method to obtain the adjusted display parameter set. Using dynamic rendering technology, a three-dimensional aging distribution image is rendered for the adjusted display parameter set to highlight the spatial location of abnormal areas and obtain the rendered three-dimensional image. Image optimization processing is used to smooth the rendered 3D image, obtain the smoothed image data, and determine the optimized visualization view. If the color contrast of abnormal areas in the optimized visualization is lower than the preset threshold, the rendering parameters are adjusted and the 3D image is re-rendered to obtain an updated visualization. Based on the updated visualization view, the distribution characteristics of the abnormal areas are extracted, spatial distribution statistics of the abnormal areas are generated, and the final visualization result is determined.

[0013] As a further preferred embodiment of the high-temperature furnace tube three-dimensional imaging detection system based on electromagnetic ultrasound and robot collaboration of the present invention, the data transmission and decision interaction module specifically includes: Aging distribution data and warning sign information are obtained from the visualization results through the data interface, and the two are integrated using information fusion technology to obtain the fused dataset. For the merged dataset, a data transmission protocol is used to transmit it to the automation system to complete the data connection and determine the marker information for the completion of the transmission; Based on the transmission completion flag, the real-time analysis module within the automation system is triggered to perform state parsing on the fused dataset and obtain the aging state analysis results. If the aging state in the analysis results exceeds the preset threshold, the decision system will generate a corresponding processing instruction and obtain the specific content of the instruction. Based on the generated processing instructions, the system interaction mechanism is used to transmit the instruction content to the relevant execution module and determine the status record of the instruction transmission. By recording the status, the system obtains the response data of the execution module to the processing instructions, determines whether the response data meets the preset execution criteria, and obtains the final feedback information. Based on the final feedback, update the aging status database within the automation system, complete data synchronization, and determine the updated status logs.

[0014] As a further preferred embodiment of the high-temperature furnace tube three-dimensional imaging detection system based on electromagnetic ultrasound and robot collaboration of the present invention, the feedback update and storage module specifically includes: The aging status feedback data is obtained through the real-time analysis module, and the dynamic identification information in the three-dimensional aging distribution is extracted by data parsing technology to determine the updated content of the identification data. If the abnormal status in the dynamic identification information exceeds the preset threshold, the display status of the abnormal area in the three-dimensional aging distribution image is adjusted by the image processing module to generate updated image data. The updated image data is transmitted to the data storage module using a data storage protocol, and the status record of the data transmission is determined. Based on the transmission status record, obtain the feedback information from the data storage module, determine whether the feedback information contains a complete abnormal status identifier, and obtain the preliminary content of the detection file; The preliminary content is structured through the archive generation module, and dynamic identification data and feedback information are integrated to determine the complete test archive. The detection files are transmitted to the aging status database using a data synchronization protocol. The update status log of the database is obtained, and it is determined whether the log reflects the latest abnormal area display status. Based on the update status log, the latest data on the 3D aging distribution in the database is obtained, triggering the image processing module to re-parse the dynamic identification information and determine the subsequent image update content.

[0015] Compared with the prior art, the present invention, employing the above technical solution, has the following technical effects: This invention relates to a high-temperature furnace tube 3D imaging inspection system based on electromagnetic ultrasound and robotic collaboration. By acquiring multi-dimensional aging data, it performs 3D reconstruction modeling of the furnace tube and generates an aging distribution image using color mapping technology. This invention can automatically identify abnormal aging areas, determine whether they are located in critical pressure-bearing areas, and generate high-priority warning labels. Through dynamic rendering technology, this invention can highlight abnormal areas and transmit the analysis results to the decision-making system in real time. This invention can also update image labels based on feedback and record inspection data, achieving precise visualization and intelligent analysis of the furnace tube aging status. This helps to promptly identify potential risks and improve equipment safety and maintenance efficiency. Attached Figure Description

[0016] Figure 1 This is a schematic diagram of the principle structure of a three-dimensional imaging detection system for high-temperature furnace tubes based on electromagnetic ultrasound and robot collaboration according to the present invention. Figure 2 This is a flowchart of a three-dimensional imaging detection system for high-temperature furnace tubes based on electromagnetic ultrasound and robot collaboration according to the present invention. Detailed Implementation

[0017] The technical solution of the present invention will be further described in detail below with reference to the accompanying drawings: The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present invention. The present invention will be described in detail below with reference to the accompanying drawings and preferred embodiments. The purpose and effects of the present invention will become clearer. It should be understood that the specific embodiments described herein are merely illustrative of the present invention and are not intended to limit the present invention.

[0018] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be described in detail below with reference to the accompanying drawings and specific embodiments.

[0019] A three-dimensional imaging inspection system for high-temperature furnace tubes based on electromagnetic ultrasound and robotic collaboration, such as Figure 1 The module includes a data acquisition and processing module, a 3D reconstruction module, a color mapping module, an anomaly annotation module, a key component judgment module, a visualization optimization module, a data transmission and decision-making interaction module, and a feedback update and storage module. The data acquisition and processing module is used to acquire multi-dimensional aging data from the high-temperature furnace tube testing equipment, classify and process the data according to the degree of material degradation and location information in different areas, and perform preliminary structuring processing on the data through preset classification rules to obtain the processed aging dataset. 3D Reconstruction Module: This module uses a 3D reconstruction algorithm to digitally model the spatial structure of the furnace tubes based on the processed aging dataset. It combines location information and aging degree data to map planar data onto a 3D spatial model, generating an initial 3D furnace tube model. Color mapping module: It is used to extract the aging degree values ​​of each region based on the initial three-dimensional furnace tube model, and to classify and identify different aging degrees through color mapping technology, generating a three-dimensional aging distribution image with color distinction. Anomaly labeling module: This module is used to analyze the distribution pattern of aging degree corresponding to color-coded 3D aging distribution images, and automatically label abnormal aging areas within a preset threshold range to obtain a labeled distribution image. Critical component judgment module: It is used to extract the spatial location information of abnormal aging areas from the labeled distribution image, and combine it with the overall structure data of the furnace tube to determine whether the abnormal area is located in a critical pressure-bearing part. If it is located in a critical part, a high-priority warning sign is generated. Visualization optimization module: Used to adjust the display parameters of the 3D aging distribution image based on high-priority warning signs, highlight the color contrast and spatial position of abnormal areas, optimize the image through dynamic rendering technology, and generate the final visualization result; Data transmission and decision interaction module: This module integrates aging distribution data and warning label information for the final visualization results, transmits them to the automated decision system through a data interface, obtains real-time analysis feedback on the aging status from the system, and determines subsequent processing instructions. Feedback update and storage module: It is used to update the dynamic label content in the three-dimensional aging distribution image based on real-time analysis feedback, synchronously adjust the display status of abnormal areas, and record the image data and feedback information of each update through the data storage module to obtain a complete detection archive.

[0020] This invention relates to a high-temperature furnace tube 3D imaging inspection system based on electromagnetic ultrasound and robotic collaboration. By acquiring multi-dimensional aging data, it performs 3D reconstruction modeling of the furnace tube and generates an aging distribution image using color mapping technology. This invention can automatically identify abnormal aging areas, determine whether they are located in critical pressure-bearing areas, and generate high-priority warning labels. Through dynamic rendering technology, this invention can highlight abnormal areas and transmit the analysis results to the decision-making system in real time. This invention can also update image labels based on feedback and record inspection data, achieving precise visualization and intelligent analysis of the furnace tube aging status. This helps to promptly identify potential risks and improve equipment safety and maintenance efficiency.

[0021] like Figure 2 As shown in the figure, the specific working process of a high-temperature furnace tube three-dimensional imaging inspection system based on electromagnetic ultrasound and robot collaboration in this embodiment is as follows: Data Acquisition and Processing Module: This module acquires multi-dimensional aging data from high-temperature furnace tube testing equipment, including material degradation degree and location information. Noise is removed using data cleaning methods to obtain cleaned aging data. Based on the cleaned aging data, material degradation degree and location information are extracted. K-means clustering is used for preliminary data classification, resulting in categorized data groups. For each categorized data group, the material degradation degree and location information are matched according to preset classification rules to determine the degradation characteristics of each group. If the degradation characteristics of a group meet a preset threshold, a support vector machine algorithm is used to further quantify the degradation degree, obtaining quantified degradation degree values. Based on the quantified degradation degree values ​​and location information, degradation distribution maps for each region are generated, determining the degradation distribution characteristics. Using these degradation distribution characteristics, a decision tree algorithm is used to predict the degradation trend of different regions, obtaining the predicted aging trend. Based on the predicted aging trend and location information, a structured aging dataset is generated, containing the degradation degree and predicted trend for each region.

[0022] 3D Reconstruction Module: For the processed aging dataset, a 3D reconstruction algorithm is used to digitize the furnace tube space, fusing location information and aging degree data to generate a preliminary 3D furnace tube model. Based on the preliminary 3D furnace tube model, key regions in the spatial structure are extracted. Combined with location information, the aging degree distribution in the model is locally divided, resulting in regional distribution data. For the divided regional distribution data, the differences in aging degree between regions are obtained, and a preset threshold is used for comparison. If the aging degree of a certain region exceeds the threshold, the spatial structure of that region is refined, resulting in refined regional structure data. Based on the refined regional structure data, the... By combining location information, the aging degree in three-dimensional space is layered and labeled to generate a three-dimensional furnace tube model with layered labels. For the three-dimensional furnace tube model with layered labels, the aging degree and spatial structure features of each layer are extracted, and the aging distribution pattern of different regions is analyzed using the support vector machine algorithm to determine the aging distribution characteristics of each region. Based on the aging distribution characteristics of each region and combined with the location information in three-dimensional space, the aging trend of the furnace tube space is compared by region to obtain regional aging trend data. For the regional aging trend data, the spatial structure and location information are integrated, and the trend data is mapped onto the three-dimensional furnace tube model to generate the final three-dimensional model with trend labels.

[0023] Color Mapping Module: For the furnace tube structure in the 3D model, aging degree information for each region is obtained. Different aging degrees are graded and labeled using a color mapping method, resulting in a color-coded distribution view. Based on the color differentiation results in the distribution view, the aging distribution characteristics of each region are extracted and compared using a preset threshold. If the aging degree of a certain region exceeds the threshold, the structural features of that region are deeply analyzed to determine the distribution of high-risk areas. For the distribution of high-risk areas, corresponding spatial data is obtained. Combined with the furnace tube structure information, these regions are locally magnified to obtain a refined local view. Based on the refined local view, local areas are extracted. The aging distribution details of the domain are analyzed, and combined with regional division information, the aging degree is annotated at multiple levels to generate a local distribution view with hierarchical annotations. For the local distribution view with hierarchical annotations, the differences in aging degree at each level are obtained, and the difference data is classified using a support vector machine algorithm to determine the aging distribution pattern of each region. Based on the results of the aging distribution pattern, combined with spatial data and structural features, the aging distribution in the furnace tube structure is dynamically updated to generate an updated three-dimensional distribution view. For the updated three-dimensional distribution view, the latest aging distribution information is obtained, and combined with regional division and hierarchical annotation data, the view is optimized and adjusted to obtain the final three-dimensional aging distribution view.

[0024] Anomaly Labeling Module: This module extracts data from color-coded 3D images to obtain aging degree information corresponding to each color. Image analysis techniques are used to initially classify the aging degree of each region, resulting in categorized aging distribution data. Based on this categorized aging distribution data, and combined with distribution pattern analysis methods, the module identifies the distribution characteristics of aging degree in different regions and determines the aging degree change trend in each region. For the aging degree change trend, corresponding region division information is obtained, and anomaly regions are compared with preset thresholds. If the aging degree of a region exceeds the preset threshold, it is marked as an anomaly region, generating labeled region data. Using the labeled region data, automatic labeling technology is used to mark the anomaly regions, generating a distribution view with labeled information. Based on the labeled distribution view, the features of the anomaly regions in the labeling results are extracted, and combined with the spatial information of the 3D image, local data enhancement is performed on the anomaly regions to obtain enhanced view data. For the enhanced view data, combined with region division and color label information, multi-level rendering processing is performed on the distribution view to generate the final labeled distribution view. Using the final labeled distribution view, the distribution pattern data of aging degree is obtained, and the distribution characteristics of the anomaly regions are classified using a support vector machine algorithm to determine the aging distribution pattern of each region.

[0025] Key component identification module: Extracts spatial coordinate data of abnormal aging areas from the labeled distribution image; uses image segmentation technology to delineate the boundaries of abnormal areas, obtaining a coordinate dataset with clear boundaries; based on this dataset and a pre-established furnace tube structure model, maps the spatial coordinates of the abnormal areas to the structural model, determining the location distribution of the abnormal areas within the furnace tube; uses the location distribution data to obtain the geometric features of pressure-bearing parts in the furnace tube structure model; if the coordinate data of the abnormal area overlaps with the geometric features of the pressure-bearing parts, the abnormal area is determined to be located within a pressure-bearing part, resulting in a pressure-bearing area identification result; based on the pressure-bearing area identification result, and combined with a pre-set list of key components, if... If the location of the pressure-bearing area matches the location in the list of key components, high-priority warning label data is generated. The spatial location and priority information of the labels are extracted from this high-priority warning label data. Rendering techniques are used to highlight the abnormal areas with color in the visualization view of the furnace tube structure model, resulting in a labeled visualization view. Based on this labeled visualization view, a distribution feature dataset of the abnormal areas is generated. The k-means clustering algorithm is used to classify the distribution patterns of the abnormal areas, resulting in classified distribution pattern data. Using the classified distribution pattern data, combined with the geometric information of the furnace tube structure model, a spatial distribution statistics table of the abnormal areas is generated to determine the distribution patterns of the abnormal areas.

[0026] The visualization optimization module: It obtains the identification data of abnormal areas from high-priority warning signs, extracts the spatial coordinates and priority information corresponding to the signs, and obtains the coordinate dataset of the abnormal areas. Based on the coordinate dataset of the abnormal areas, it obtains the current display parameters of the 3D aging distribution image, adjusts the color contrast using a parameter mapping method, and obtains the adjusted display parameter set. Using dynamic rendering technology, it renders the 3D aging distribution image based on the adjusted display parameter set, highlighting the spatial location of the abnormal areas, and obtains the rendered 3D image. Through image optimization processing, it smooths the rendered 3D image, obtains the smoothed image data, and determines the optimized visualization view. If the color contrast of the abnormal areas in the optimized visualization view is lower than a preset threshold, it adjusts the rendering parameters and re-renders the 3D image, obtaining an updated visualization view. Based on the updated visualization view, it extracts the distribution characteristics of the abnormal areas, generates spatial distribution statistics of the abnormal areas, and determines the final visualization result.

[0027] The data transmission and decision-making interaction module: It acquires aging distribution data and warning label information from the visualization results via a data interface, integrates these two data points using information fusion technology to obtain a fused dataset. For this fused dataset, it transmits it to the automation system using a data transmission protocol, completing data integration and identifying a transmission completion marker. Based on this marker, the real-time analysis module within the automation system is triggered to perform state analysis on the fused dataset, obtaining the aging state analysis results. If the aging state exceeds a preset threshold, the decision-making system generates a corresponding processing instruction, acquiring its specific content. Based on the generated processing instruction, the system interaction mechanism transmits the instruction content to the relevant execution module, determining the instruction transmission status record. Using the status record, it acquires the execution module's response data to the processing instruction, determines whether the response data meets preset execution standards, and obtains the final feedback information. Based on the final feedback information, it updates the aging state database within the automation system, completing data synchronization and determining the updated status log.

[0028] Feedback Update and Storage Module: This module acquires aging status feedback data through a real-time analysis module, extracts dynamic identifier information from the 3D aging distribution using data parsing technology, and determines the update content of the identifier data. If the abnormal status in the dynamic identifier information exceeds a preset threshold, the image processing module adjusts the display status of abnormal areas in the 3D aging distribution image, generating updated image data. The updated image data is then transmitted to the data storage module using a data storage protocol, and the data transmission status record is maintained. Based on the transmission status record, feedback information from the data storage module is obtained, and it is determined whether the feedback information contains complete abnormal status identifiers, thus obtaining the preliminary content of the detection file. The file generation module performs structured processing on the preliminary content, integrating the dynamic identifier data and feedback information to determine the complete detection file. The detection file is transmitted to the aging status database using a data synchronization protocol, and the update status log of the database is obtained. It is determined whether the log reflects the latest abnormal area display status. Based on the update status log, the latest data of the 3D aging distribution in the database is obtained, triggering the image processing module to re-parse the dynamic identifier information and determine the subsequent image update content.

[0029] Specific embodiments of the present invention have been described above. It should be understood that the present invention is not limited to the specific embodiments described above, and those skilled in the art can make various changes or modifications within the scope of the claims, which do not affect the essence of the present invention. Unless otherwise specified, the embodiments and features described in this application can be arbitrarily combined with each other.

[0030] It will be understood by those skilled in the art that the above descriptions are merely preferred examples of the invention and are not intended to limit the invention. Although the invention has been described in detail with reference to the foregoing examples, those skilled in the art can still modify the technical solutions described in the foregoing examples or make equivalent substitutions for some of the technical features. All modifications and equivalent substitutions made within the spirit and principles of the invention should be included within the scope of protection of the invention. All technical features in this embodiment can be freely combined according to actual needs.

[0031] Finally, it should be noted that the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing embodiments or make equivalent substitutions for some of the technical features. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A three-dimensional imaging inspection system for high-temperature furnace tubes based on electromagnetic ultrasound and robotic collaboration, characterized in that: It includes modules for data acquisition and processing, 3D reconstruction, color mapping, anomaly annotation, key component identification, visualization optimization, data transmission and decision-making interaction, and feedback update and storage. The data acquisition and processing module is used to acquire multi-dimensional aging data from the high-temperature furnace tube testing equipment, classify and process the data according to the degree of material degradation and location information in different areas, and perform preliminary structuring processing on the data through preset classification rules to obtain the processed aging dataset. 3D Reconstruction Module: This module uses a 3D reconstruction algorithm to digitally model the spatial structure of the furnace tubes based on the processed aging dataset. It combines location information and aging degree data to map planar data onto a 3D spatial model, generating an initial 3D furnace tube model. Color mapping module: It is used to extract the aging degree values ​​of each region based on the initial three-dimensional furnace tube model, and to classify and identify different aging degrees through color mapping technology, generating a three-dimensional aging distribution image with color distinction. Anomaly labeling module: This module is used to analyze the distribution pattern of aging degree corresponding to color-coded 3D aging distribution images, and automatically label abnormal aging areas within a preset threshold range to obtain a labeled distribution image. Critical component judgment module: It is used to extract the spatial location information of abnormal aging areas from the labeled distribution image, and combine it with the overall structure data of the furnace tube to determine whether the abnormal area is located in a critical pressure-bearing part. If it is located in a critical part, a high-priority warning sign is generated. Visualization optimization module: Used to adjust the display parameters of the 3D aging distribution image based on high-priority warning signs, highlight the color contrast and spatial position of abnormal areas, optimize the image through dynamic rendering technology, and generate the final visualization result; Data transmission and decision interaction module: This module integrates aging distribution data and warning label information for the final visualization results, transmits them to the automated decision system through a data interface, obtains real-time analysis feedback on the aging status from the system, and determines subsequent processing instructions. Feedback update and storage module: It is used to update the dynamic label content in the three-dimensional aging distribution image based on real-time analysis feedback, synchronously adjust the display status of abnormal areas, and record the image data and feedback information of each update through the data storage module to obtain a complete detection archive.

2. The high-temperature furnace tube three-dimensional imaging inspection system based on electromagnetic ultrasound and robot collaboration according to claim 1, characterized in that, The data acquisition and processing module specifically includes: Multi-dimensional aging data, including the degree of material degradation and location information, is obtained from high-temperature furnace tube testing equipment. Noise is removed by data cleaning methods to obtain cleaned aging data. Based on the aging data after cleaning, the degree and location information of material degradation are extracted, and the K-means clustering algorithm is used to preliminarily classify the data to obtain the classified data groups; Based on the categorized data groups, and combined with the preset categorization rules, the degree of material degradation and location information are matched to determine the degradation characteristics of each group; If the degradation characteristics of the group meet the preset threshold, the support vector machine algorithm is used to further quantify the degradation degree to obtain the quantified degradation degree value. Based on the quantified degradation level values ​​and location information, degradation distribution maps for each region are generated to determine the degradation distribution characteristics. By analyzing the degradation distribution characteristics, a decision tree algorithm is used to predict the degradation trend in different regions, thus obtaining the predicted aging trend. Based on the predicted aging trends, a structured aging dataset is generated by combining location information, which includes the degree of degradation and predicted trends of each region.

3. The high-temperature furnace tube three-dimensional imaging inspection system based on electromagnetic ultrasound and robot collaboration according to claim 1, characterized in that, The three-dimensional reconstruction module specifically includes: For the sorted aging dataset, a three-dimensional reconstruction algorithm is used to digitize the furnace tube space, and the location information and aging degree data are integrated to generate a preliminary three-dimensional furnace tube model. Based on the preliminary three-dimensional furnace tube model, key areas in the spatial structure are extracted. Combined with location information, the aging degree distribution in the model is locally divided to obtain the regional distribution data after division. For the divided regional distribution data, the differences in aging degree of each region are obtained and compared using a preset threshold. If the aging degree of a certain region exceeds the threshold, the spatial structure of that region is refined to obtain refined regional structure data. Based on the refined regional structure data and combined with location information, the aging degree in three-dimensional space is labeled in layers to generate a three-dimensional furnace tube model with layered labels. For a three-dimensional furnace tube model with layered annotations, the aging degree and spatial structure features of each layer are extracted. The support vector machine algorithm is used to analyze the aging distribution pattern of different regions and determine the aging distribution characteristics of each region. Based on the aging distribution characteristics of each region and combined with the location information in three-dimensional space, the aging trend of the furnace tube space is compared by region to obtain the aging trend data of each region. Based on the aging trend data of different regions, spatial structure and location information are integrated, and the trend data is mapped onto the three-dimensional furnace tube model to generate the final three-dimensional model with trend annotations.

4. The high-temperature furnace tube three-dimensional imaging inspection system based on electromagnetic ultrasound and robot collaboration according to claim 1, characterized in that, The color mapping module specifically includes: For the furnace tube structure in the 3D model, the aging degree information of each region is obtained, and the different aging degrees are graded and labeled by color mapping method to obtain a distribution view with color differentiation. Based on the color differentiation results in the distribution view, the aging distribution characteristics of each region are extracted and compared using a preset threshold. If the aging degree of a certain region exceeds the threshold, the structural characteristics of that region are analyzed in depth to determine the distribution of high-risk regions. Based on the distribution of high-risk areas, corresponding spatial data is obtained, and combined with furnace tube structure information, these areas are locally magnified to obtain a refined local view. Based on the refined local view, the aging distribution details of the local area are extracted. Combined with the area division information, the degree of aging is annotated in multiple layers to generate a local distribution view with hierarchical annotations. For a local distribution view with hierarchical labeling, the differences in aging degree at each level are obtained. The support vector machine algorithm is used to classify the difference data and determine the aging distribution pattern of each region. Based on the results of the aging distribution pattern, combined with spatial data and structural features, the aging distribution in the furnace tube structure is dynamically updated to generate an updated three-dimensional distribution view. For the updated 3D distribution view, the latest aging distribution information is obtained. Combined with the regional division and hierarchical labeling data, the view is optimized and adjusted to obtain the final 3D aging distribution view.

5. The high-temperature furnace tube three-dimensional imaging inspection system based on electromagnetic ultrasound and robot collaboration according to claim 1, characterized in that, The anomaly annotation module specifically includes: By extracting data from 3D images with color distinctions, the aging degree information corresponding to the color labels is obtained. Image analysis technology is used to preliminarily classify the aging degree of each region, and the aging distribution data after classification is obtained. Based on the categorized aging distribution data and combined with the analysis method of distribution patterns, the distribution characteristics of aging degree in different regions are identified, and the changing trend of aging degree in each region is determined. Based on the trend of aging, the corresponding regional division information is obtained, and abnormal regions are compared with preset thresholds. If the aging of a certain region exceeds the preset threshold, it is marked as an abnormal region, and the marked region data is generated. Using the marked area data, anomalies are identified through automatic annotation technology, generating a distribution view with annotation information. Based on the distribution view with annotation information, the abnormal area features in the annotation results are extracted, and combined with the spatial information of the 3D image, the abnormal area is locally augmented to obtain the augmented view data. Based on the enhanced view data, and combined with region division and color identification information, the distribution view is subjected to multi-level rendering processing to generate the final labeled distribution view; By using the final labeled distribution view, the distribution pattern data of aging degree is obtained. The distribution characteristics of abnormal areas are classified by combining the support vector machine algorithm to determine the aging distribution pattern of each area.

6. The high-temperature furnace tube three-dimensional imaging inspection system based on electromagnetic ultrasound and robot collaboration according to claim 1, characterized in that, The critical component determination module specifically includes: Spatial coordinate data of abnormal aging regions are extracted from the labeled distribution image. Image segmentation technology is used to divide the boundaries of the abnormal regions to obtain a coordinate dataset with clear boundaries. Based on a well-defined coordinate dataset and a pre-established furnace tube structure model, the spatial coordinates of the abnormal region are mapped to the structure model to determine the location distribution of the abnormal region in the furnace tube. By using location distribution data, the geometric features of the pressure-bearing parts in the furnace tube structure model are obtained. If the coordinate data of the abnormal area overlaps with the geometric features of the pressure-bearing parts, the abnormal area is determined to be located in the pressure-bearing parts, and the pressure-bearing area judgment result is obtained. Based on the assessment results of the pressure-bearing area, and combined with the pre-set list of key parts, if the pressure-bearing area matches the location in the list of key parts, high-priority warning label data is generated. The spatial location and priority information of the high-priority warning signs are extracted from the data. The abnormal areas are highlighted with color in the visualization view of the furnace tube structure model using rendering technology to obtain the highlighted visualization view. Based on the labeled visualization view, a dataset of distribution features of abnormal regions is generated. The k-means clustering algorithm is used to classify the distribution patterns of abnormal regions, and the classified distribution pattern data is obtained. By combining the categorized distribution pattern data with the geometric information of the furnace tube structure model, a spatial distribution statistical table of abnormal areas is generated to determine the distribution pattern of abnormal areas.

7. The high-temperature furnace tube three-dimensional imaging inspection system based on electromagnetic ultrasound and robot collaboration according to claim 1, characterized in that, The visualization optimization module specifically includes: Obtain the identification data of the abnormal area from the high-priority warning signs, extract the spatial coordinates and priority information corresponding to the signs, and obtain the coordinate dataset of the abnormal area. Based on the coordinate dataset of the abnormal region, the current display parameters of the three-dimensional aging distribution image are obtained, and the color contrast is adjusted using a parameter mapping method to obtain the adjusted display parameter set. Using dynamic rendering technology, a three-dimensional aging distribution image is rendered for the adjusted display parameter set to highlight the spatial location of abnormal areas and obtain the rendered three-dimensional image. Image optimization processing is used to smooth the rendered 3D image, obtain the smoothed image data, and determine the optimized visualization view. If the color contrast of abnormal areas in the optimized visualization is lower than the preset threshold, the rendering parameters are adjusted and the 3D image is re-rendered to obtain an updated visualization. Based on the updated visualization view, the distribution characteristics of the abnormal areas are extracted, spatial distribution statistics of the abnormal areas are generated, and the final visualization result is determined.

8. The high-temperature furnace tube three-dimensional imaging inspection system based on electromagnetic ultrasound and robot collaboration according to claim 1, characterized in that, The data transmission and decision-making interaction module specifically includes: Aging distribution data and warning sign information are obtained from the visualization results through the data interface, and the two are integrated using information fusion technology to obtain the fused dataset. For the merged dataset, a data transmission protocol is used to transmit it to the automation system to complete the data connection and determine the marker information for the completion of the transmission; Based on the transmission completion flag, the real-time analysis module within the automation system is triggered to perform state parsing on the fused dataset and obtain the aging state analysis results. If the aging state in the analysis results exceeds the preset threshold, the decision system will generate a corresponding processing instruction and obtain the specific content of the instruction. Based on the generated processing instructions, the system interaction mechanism is used to transmit the instruction content to the relevant execution module and determine the status record of the instruction transmission. By recording the status, the system obtains the response data of the execution module to the processing instructions, determines whether the response data meets the preset execution criteria, and obtains the final feedback information. Based on the final feedback, update the aging status database within the automation system, complete data synchronization, and determine the updated status logs.

9. The high-temperature furnace tube three-dimensional imaging inspection system based on electromagnetic ultrasound and robot collaboration according to claim 1, characterized in that, The feedback update and storage module specifically includes: The aging status feedback data is obtained through the real-time analysis module, and the dynamic identification information in the three-dimensional aging distribution is extracted by data parsing technology to determine the updated content of the identification data. If the abnormal status in the dynamic identification information exceeds the preset threshold, the display status of the abnormal area in the three-dimensional aging distribution image is adjusted by the image processing module to generate updated image data. The updated image data is transmitted to the data storage module using a data storage protocol, and the status record of the data transmission is determined. Based on the transmission status record, obtain the feedback information from the data storage module, determine whether the feedback information contains a complete abnormal status identifier, and obtain the preliminary content of the detection file; The preliminary content is structured through the archive generation module, and dynamic identification data and feedback information are integrated to determine the complete test archive. The detection files are transmitted to the aging status database using a data synchronization protocol. The update status log of the database is obtained, and it is determined whether the log reflects the latest abnormal area display status. Based on the update status log, the latest data on the 3D aging distribution in the database is obtained, triggering the image processing module to re-parse the dynamic identification information and determine the subsequent image update content.

Images