Welding opening firmness detection system and method

Abstract

The invention discloses a welding opening firmness detection system and method, and relates to the technical field of welding opening detection, and the system comprises a welding parameter collection module, a welding opening firmness abnormity judgment module, a multi-mode detection module, a self-adaptive robot, an intelligent analysis module and a data bin. Whether the welding position of the pipeline needs firmness detection or not is judged according to the prior data of the laid pipeline, firmness detection efficiency is improved, abnormal conditions in construction are responded, and detection pertinence is guaranteed; according to the method, the potential identification defects at the welding position of the laid pipeline are identified, the potential defects of the laid pipeline in the application process are pre-judged, the existence of reserved hidden dangers is reduced, the effect of detecting the firmness of the welding opening of the laid pipeline is improved, and powerful data support is provided for subsequent rewelding; according to the invention, the firmness of the welding port of the large-diameter pipeline is detected by carrying the self-adaptive robot module, so that the objectivity of detection and the uniformity of standards are guaranteed.

Description

Technical Field

[0001] The present invention relates to the technical field of welding joint detection, and in particular to a welding joint firmness detection system and method. Background Art

[0002] Large-diameter pipelines carry the necessities of transporting critical materials such as energy, chemical raw materials, and water. The welding process for large-diameter pipelines is complex, and the joint security faced multiple challenges. Testing the security of welds between pipelines is not only a touchstone of project quality but also a safeguard for industrial safety and sustainable development. Once a weld fails, repairs require stopping the pipeline, cutting, and re-welding, resulting in significant losses.

[0003] In the existing technology, there are few methods for judging whether the pipeline welding joints need to be tested for firmness based on the prior data of the laid pipeline, resulting in low efficiency of firmness detection, inability to respond to abnormal situations during construction in a timely manner, and reduced detection targeting. At the same time, there are few methods for identifying potential defects in the welds of the laid pipelines, making it difficult to predict potential defects in the laid pipelines during application, leaving hidden dangers, reducing the effectiveness of the firmness detection of the welds of the laid pipelines, and making it difficult to provide strong data support for subsequent re-welding. Summary of the Invention

[0004] The purpose of the present invention is to provide a welding joint firmness detection system and method, which solve the problems existing in the background technology.

[0005] In order to solve the above technical problems, the present invention adopts the following technical solutions: In a first aspect, the present invention provides a welding joint firmness detection system, comprising: a welding parameter collection module for collecting a set of welding parameters of the welding joints of the laid pipeline.

[0006] The welding joint firmness abnormality judgment module generates a welding joint firmness index set for the laid pipeline based on the welding parameter set of the welding joint of the laid pipeline, and judges whether the several welding joints of the laid pipeline are firm abnormal based on the welding joint firmness index minus the firmness abnormality level. If abnormal, the multimodal detection module and the adaptive robot are activated.

[0007] The multimodal detection module integrates an ultrasonic phased array detection unit, a pulsed eddy current detection unit, a laser 3D scanning unit, a dynamic load strength verification unit, and a thermal imaging unit. It is used to synchronously obtain the surface model of the weld, the type of internal defects, geometric dimensions, and position information, as well as the defects, geometric dimensions, position information, direction, stress and deformation data, and heat conduction data of the pipe wall.

[0008] The adaptive robot is equipped with a retractable track and modular detection modules. It automatically adapts to the inner wall of the pipeline through hydraulic or robotic arm structure and supports rapid replacement of ultrasonic phased array detection units, pulsed eddy current detection units, laser 3D scanning units, dynamic load strength verification units and thermal imaging units.

[0009] The intelligent analysis module classifies and integrates multimodal detection data, automatically identifies visible defect sets and potential defect sets, and simultaneously generates a weld joint firmness detection report.

[0010] A second aspect of the present invention provides a method for the weld joint firmness detection system of the present invention, comprising: S1, collecting a set of welding parameters of the weld joints of the laid pipeline.

[0011] S2. A set of welding parameters of the weld joints of the laid pipeline is generated to generate a set of weld joint firmness indexes of the laid pipeline. It is determined whether the weld joints of the laid pipeline have firmness abnormalities according to the weld joint firmness index minus the firmness abnormality level. If so, S3 is executed.

[0012] S3. The adaptive robot is driven by a hydraulic or mechanical arm structure to automatically adapt to the inner wall of the pipeline and crawl. The adaptive robot is provided with a retractable track and a modular detection module.

[0013] S4. Classify and integrate multimodal inspection data, automatically identify visible defect sets and potential defect sets, and simultaneously generate weld joint firmness inspection reports.

[0014] The beneficial effects of the present invention are: (1) the present invention determines whether the pipeline welding joints need to be tested for firmness based on the prior data of the pipeline laying, thereby improving the efficiency of firmness testing, responding to abnormal conditions during construction, and ensuring the targeted nature of the testing.

[0015] (2) The present invention applies load to the weld joint through a dynamic load strength verification unit and collects stress deformation data, thereby identifying potential defects in the weld joint of the laid pipeline, predicting potential defects in the laid pipeline during application, reducing the existence of reserved hidden dangers, improving the effect of the weld joint firmness detection of the laid pipeline, and providing strong data support for subsequent re-welding.

[0016] (3) The present invention carries out a firmness test on the welding joints of large-diameter pipes by equipping them with an adaptive robot module, thereby avoiding reliance on manual testing and ensuring the objectivity of the test and the uniformity of the standards. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0018] Figure 1 This is a schematic diagram of the system structure connection of the present invention.

[0019] Figure 2 The figure is a flow chart of the steps for implementing the method of the present invention. DETAILED DESCRIPTION

[0020] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0021] Reference Figure 1 As shown, the first aspect of the present invention provides a welding joint firmness detection system, including: a welding parameter collection module, collecting a welding parameter set of the welding joint of the laid pipeline.

[0022] It should be noted that the method of collecting the welding parameter set of the welding joints of the laid pipeline is relatively simple in the existing technology, and the technology is relatively mature, so it will not be described in detail here.

[0023] The welding joint firmness abnormality judgment module generates a welding joint firmness index set for the laid pipeline based on the welding parameter set of the welding joint of the laid pipeline, and judges whether the several welding joints of the laid pipeline are firm abnormal based on the welding joint firmness index minus the firmness abnormality level. If abnormal, the multimodal detection module and the adaptive robot are activated.

[0024] In a specific embodiment of the present invention, the welding parameter set of the welding joint includes welding pre-parameters and welding process parameters of several welding joints, the welding pre-parameters specifically refer to the layout data of the welding joint before welding, and the welding process parameters specifically refer to the control data of the welding joint during the welding process.

[0025] In a specific embodiment of the present invention, a set of firmness indexes of the weld joints of the laid pipeline is generated based on a set of welding parameters of the weld joints of the laid pipeline. The specific generation method is as follows: a plurality of welding pre-parameters and welding process parameters of the weld joints are extracted from the set of welding parameters of the weld joints of the laid pipeline, and a first firmness index is determined based on the welding pre-parameters, and a second firmness index is determined based on the welding process parameters.

[0026] According to the historical response events stored in the data warehouse, the first firmness indicator threshold a′ and the second firmness indicator threshold b′ are identified, and the probability factor of the first firmness indicator and the firmness anomaly and the probability factor of the second firmness indicator and the firmness anomaly are constructed, respectively recorded as the first probability factor and the second probability factor, and the third firmness indicator threshold C is determined.

[0027] It should be noted that the identification of the first and second robustness indicator thresholds based on the historical response events stored in the data warehouse, and the construction of the first and second probability factors are specifically carried out as follows:

[0028] A welding parameter set and a firmness abnormality feedback value of each historical welding event are extracted from the historical response event. The firmness abnormality feedback value includes values ​​of 1 and -1. When the firmness abnormality feedback value is 1, it indicates that the welding firmness is abnormal. When the firmness abnormality feedback value is -1, it indicates that the welding firmness is normal. The first firmness index and the second firmness index are obtained through similar processing.

[0029] Arrange the first and second firmness indicators of each historical welding event when all firmness abnormality feedback values ​​are -1, take the maximum first firmness indicator + safety compensation value as the first firmness indicator threshold, and take the maximum second firmness indicator + safety compensation value as the second firmness indicator threshold.

[0030] Arrange the first firmness index and the second firmness index of each historical welding event when all firmness abnormality feedback values ​​are 1, and solve the probability factor of the first firmness index and firmness abnormality, the probability factor of the second firmness index and firmness abnormality, and the threshold value of the third firmness abnormality index through linear regression or a set of equations.

[0031] Exemplarily, for each historical welding event of all firmness abnormality feedback values ​​1, a*a1+b*b1≥C is satisfied, where a and b represent the first firmness index and the second firmness index, a1 and b1 represent the first probability factor and the second probability factor, and C represents the third firmness abnormality index threshold.

[0032] Import the first firmness index a, the second firmness index b, the first probability factor a1, and the second probability factor b1 of several welding joints into the firmness index model In the test, the firmness indexes of several welding joints are output. When the firmness index of the welding joint is 0, it means that the firmness of the welding joint is abnormal. When the firmness index of the welding joint is 1, it means that the firmness of the welding joint is normal.

[0033] In a specific embodiment of the present invention, the first firmness index is determined according to the welding pre-parameters, and the specific determination method is: the welding pre-parameters include several characteristic parameters of their own states, and the several characteristic parameters of their own states specifically reflect the layout quality before welding.

[0034] It should be noted that the characteristic parameters of the several self-states include but are not limited to groove angle, blunt edge thickness, root gap length, misalignment and surface defect type, and the surface defect type includes impurities such as oil, rust, and moisture.

[0035] The characteristic parameters of several self-states of several welded joints of the laid pipeline are compared with the design safety margins of several self-states of the laying process stored in the data warehouse. If the characteristic parameter of a certain self-state is not within the corresponding design safety margin, the abnormal value of the characteristic parameter of the self-state is recorded as 1. In this way, the abnormal values ​​of the characteristic parameters of several self-states of several welded joints of the laid pipeline are obtained, and the average values ​​are processed to obtain the first firmness index of the several welded joints of the laid pipeline.

[0036] In a specific embodiment of the present invention, the second firmness index is determined according to the welding process parameters, and the specific determination method is: the welding process parameters include characteristic parameters of several welding parameters, and the characteristic parameters of the several welding parameters specifically reflect the quality of the welding process.

[0037] It should be noted that the characteristic parameters of the welding parameters include the maximum peak value of current, the minimum valley value of current, the average welding current, the current fluctuation, the welding speed fluctuation, the average welding speed, the average gas flow rate, the gas flow rate fluctuation, the electrode state value, etc. The electrode state value specifically quantifies whether the motor has defects, and the defects include wear or contamination, etc., and contains values ​​0 and 1. When the motor state value is 1, it indicates that the motor is in good condition and there is no defect. When the electrode state value is 0, it indicates that the motor is abnormal and there is a defect.

[0038] It should be added again that the welding process parameters are specifically limited by the welding process and are obtained based on the welding process adopted. For example, gas shielded welding requires monitoring of gas usage, while gas shielded welding does not require monitoring of gas usage. The above welding process parameters are only used as examples. In actual applications, specific selection is made based on the welding process combined with the welding process-monitoring welding parameter mapping table preset in the data warehouse.

[0039] The welding process-monitoring welding parameter mapping table is specifically formulated by welding engineers.

[0040] The characteristic parameters of the welding parameters of the welded joints of the pipeline are processed in the same manner as the characteristic parameters of the states of the welded joints of the pipeline, so as to obtain the second firmness indexes of the welded joints of the pipeline.

[0041] The present invention determines whether a pipeline welding position needs a firmness test based on prior data of pipeline laying, thereby improving the efficiency of firmness test, responding to abnormal situations during construction, and ensuring the pertinence of the test.

[0042] The multimodal detection module integrates an ultrasonic phased array detection unit, a pulsed eddy current detection unit, a laser 3D scanning unit, a dynamic load strength verification unit, and a thermal imaging unit. It is used to synchronously obtain the surface model of the weld, the type of internal defects, geometric dimensions, and position information, as well as the defects, geometric dimensions, position information, direction, stress and deformation data, and heat conduction data of the pipe wall.

[0043] It should be noted that the ultrasonic phased array detection unit is specifically used to detect the internal defect type, geometric dimensions, and position information of the welding joint; the pulsed eddy current detection unit is specifically used to detect the defects, geometric dimensions, position information, and direction of the pipe wall; the dynamic load strength verification unit is specifically used to apply load to the welding joint and collect force and deformation data; the thermal imaging unit specifically uses terahertz waves to collect heat conduction data after welding is completed, breaking through the limitation of traditional non-destructive testing that requires waiting for the workpiece to completely cool down.

[0044] In a specific embodiment of the present invention, the content of executing the ultrasonic phased array detection unit further includes: performing rapid three-dimensional modeling of multiple weld joints of the laid pipeline, and determining the scanning angles, focal laws, and start and end chip parameters of the multiple weld joints based on the three-dimensional models. Specifically, the content includes the following: extracting a stored weld joint model-ultrasonic phased array detection parameter mapping table from a data warehouse, importing the three-dimensional models of the multiple weld joints of the laid pipeline and multiple example three-dimensional models in the weld joint model-ultrasonic phased array detection parameter mapping table into a model similarity evaluation model, outputting the similarity between the three-dimensional models of the multiple weld joints and the multiple example three-dimensional models, and selecting the ultrasonic phased array detection parameters of the example three-dimensional model corresponding to the maximum similarity as the ultrasonic phased array detection parameters of the weld joint, wherein the ultrasonic phased array detection parameters include the scanning angle, focal law, and start and end chip parameters.

[0045] It should be noted that, referring to the invention patent application with publication number CN119901816A, which discloses an ultrasonic phased array automatic detection device and method for welded joints, and the invention patent application with publication number CN118658800B, which discloses an integrated circuit package sealing detection method and system based on composite metamaterials, the basic principle of the ultrasonic phased array detection unit can be understood. In the prior art, when executing the ultrasonic phased array detection unit, it is necessary to model the weld joint and determine the scanning angle, focusing law, and start and end chip parameters of the weld joint through a series of simulations. Although it can ensure the effectiveness and accuracy of ultrasonic phased array detection, it is time-consuming. Based on this, the present application improves it and constructs ultrasonic phased array detection parameters corresponding to different three-dimensional models according to the three-dimensional model of the weld joint. The problem of ensuring the effectiveness and accuracy of ultrasonic phased array detection is simplified to the evaluation of the similarity of the weld joint model, which greatly reduces the time for determining the ultrasonic phased array detection parameters of the weld joint, ensuring the effectiveness and accuracy of ultrasonic phased array detection while also improving efficiency.

[0046] It should also be noted that the method of importing two three-dimensional models into the model similarity evaluation model and outputting the similarity is relatively simple and easy to implement, and will not be described in detail here.

[0047] The adaptive robot is equipped with a retractable track and modular detection modules. It automatically adapts to the inner wall of the pipeline through hydraulic or robotic arm structure and supports rapid replacement of ultrasonic phased array detection units, pulsed eddy current detection units, laser 3D scanning units, dynamic load strength verification units and thermal imaging units.

[0048] The present invention carries out a firmness test on the welding joints of large-diameter pipelines by equipping an adaptive robot module, avoiding reliance on manual testing, thereby ensuring the objectivity of the test and the uniformity of the standards.

[0049] The intelligent analysis module classifies and integrates multimodal detection data, automatically identifies visible defect sets and potential defect sets, and simultaneously generates a weld joint firmness detection report.

[0050] It should be noted that the apparent defect set specifically includes the internal defect type, geometric size, position information of the weld, and the defects, geometric size, position information, and direction of the pipe wall.

[0051] In a specific embodiment of the present invention, the automatic identification of potential defect sets, the specific identification method is: obtaining a displacement vector field based on the stress and deformation data of several welds of the laid pipeline, and calculating the strain field based on the displacement vector field, and calculating the maximum principal strain ε1 field, equivalent strain ε0q field, displacement discontinuity D field, and strain concentration factor K field. The stress and deformation data include images before deformation and images after deformation.

[0052] It should be noted that the physical meaning of the maximum principal strain is the maximum tensile / compressive strain that the material can withstand, which reflects the degree of local stress concentration. The physical meaning of the equivalent strain is the Mises equivalent plastic strain of the comprehensive shear and normal strain, which predicts material yield. The physical meaning of the displacement discontinuity is the jump amplitude of the displacement vectors of adjacent points, which characterizes macroscopic cracks. The physical meaning of the strain concentration factor is the ratio of local strain to global average strain, which reveals geometric defects. The specific calculation formula is a general formula and will not be elaborated here.

[0053] The strain field characteristics are identified, and the defect type-strain field characteristic mapping table stored in the data warehouse is traversed to output several potential defects of several weld joints of the laid pipeline.

[0054] It should be noted that, taking the defect types of surface cracks and internal pores as an example, the strain field characteristics corresponding to the surface cracks are that the maximum principal strain ε1 field presents a dumbbell-shaped double peak, and the D value is continuously high along the crack path. The strain field characteristics corresponding to the internal pores are that the equivalent strain ε0q field presents a closed loop high value, and the central strain is close to 0.

[0055] Based on the heat conduction data of several welded joints of the laid pipeline, which includes terahertz wave reflection signals in several regions, the temperature gradient abnormal regions of the several welded joints of the laid pipeline are identified, namely, potential abnormal regions.

[0056] The present invention applies load to the weld joint through a dynamic load strength verification unit and collects stress deformation data, thereby identifying potential defects in the weld of the laid pipeline, predicting potential defects of the laid pipeline during application, reducing the existence of reserved hidden dangers, improving the effect of the weld joint firmness detection of the laid pipeline, and providing strong data support for subsequent re-welding.

[0057] In a specific embodiment of the present invention, the displacement vector field is specifically calculated from the images before and after deformation by a correlation function, reflecting the overall deformation.

[0058] It should be noted that the correlation between each sub-region in the image before deformation and each sub-region after deformation is calculated through the correlation function, and the position of the maximum value is selected as the displacement vector of the sub-region to be determined, so as to accurately find the displacement vector of each sub-region. The calculation of the correlation function is relatively mature in the existing technology and will not be elaborated here.

[0059] In a specific embodiment of the present invention, the identification of abnormal temperature gradient areas of several weld joints of the laid pipeline is specifically obtained by extracting several solder material data based on the terahertz wave reflection signal and several designed solder material data of the weld joints stored in the data warehouse.

[0060] It should be noted that the solder material data include but are not limited to dielectric constant and density.

[0061] Specifically, if certain solder material data of a certain area does not match the corresponding designed solder material data, the area is recorded as an abnormal temperature gradient area.

[0062] It should be noted that the present invention also includes a data warehouse for storing data required for welding joint firmness detection.

[0063] Reference Figure 2 As shown, the second aspect of the present invention provides a method for the welding joint firmness detection system of the present invention, comprising: S1, collecting a set of welding parameters of the welding joints of the laid pipeline.

[0064] S2. A set of welding parameters of the weld joints of the laid pipeline is generated to generate a set of weld joint firmness indexes of the laid pipeline. It is determined whether the weld joints of the laid pipeline have firmness abnormalities according to the weld joint firmness index minus the firmness abnormality level. If so, S3 is executed.

[0065] S3. The adaptive robot is driven by a hydraulic or mechanical arm structure to automatically adapt to the inner wall of the pipeline and crawl. The adaptive robot is provided with a retractable track and a modular detection module.

[0066] S4. Classify and integrate multimodal inspection data, automatically identify visible defect sets and potential defect sets, and simultaneously generate weld joint firmness inspection reports.

[0067] The above content is merely an example and explanation of the concept of the present invention. Those skilled in the art may make various modifications or additions to the described specific embodiments or replace them in a similar manner. As long as they do not deviate from the concept of the invention or exceed the scope defined by the present invention, they should all fall within the scope of protection of the present invention.

Claims

1. A welding joint firmness detection system, characterized in that: include: Welding parameter collection module, collecting welding parameter sets of the weld joints of the laid pipeline; A weld joint firmness abnormality judgment module generates a weld joint firmness index set for the pipeline according to a set of welding parameters of the weld joints of the pipeline, and judges whether the weld joints of the pipeline have firmness abnormalities according to the weld joint firmness index minus the firmness abnormality level. If abnormal, the multimodal detection module and the adaptive robot are activated; Multimodal detection module, integrating ultrasonic phased array detection unit, pulsed eddy current detection unit, laser 3D scanning unit, dynamic load strength verification unit and thermal imaging unit, is used to simultaneously obtain the surface model of the weld, internal defect type, geometric dimensions, location information, pipe wall defects, geometric dimensions, location information, direction, stress deformation data and heat conduction data; The adaptive robot is equipped with a retractable track and modular detection modules. It automatically adapts to the inner wall of the pipeline through hydraulic or mechanical arm structures and supports the rapid replacement of ultrasonic phased array detection units, pulsed eddy current detection units, laser 3D scanning units, dynamic load strength verification units and thermal imaging units. The intelligent analysis module classifies and integrates multimodal detection data, automatically identifies visible defect sets and potential defect sets, and simultaneously generates a weld joint firmness detection report.

2. A welding joint firmness detection system according to claim 1, characterized in that: The welding parameter set of the welding joint includes welding pre-parameters and welding process parameters of several welding joints. The welding pre-parameters specifically refer to the layout data of the welding joint before welding, and the welding process parameters specifically refer to the control data of the welding joint during the welding process.

3. A welding joint firmness detection system according to claim 2, characterized in that: The method for generating a set of firmness indexes of the weld joints of the laid pipelines according to the set of welding parameters of the weld joints of the laid pipelines is as follows: Extracting welding pre-parameters and welding process parameters of a plurality of welding joints from a welding parameter set of a laid pipeline, and determining a first firmness index according to the welding pre-parameters, and determining a second firmness index according to the welding process parameters; Based on the historical response events stored in the data warehouse, identify the first robustness indicator threshold a′ and the second robustness indicator threshold b′, ​​and construct the probability factor of the first robustness indicator and the robustness anomaly and the probability factor of the second robustness indicator and the robustness anomaly, respectively denoted as the first probability factor and the second probability factor, and determine the third robustness indicator threshold C; Import the first firmness index a, the second firmness index b, the first probability factor a1, and the second probability factor b1 of several welding joints into the firmness index model In the test, the firmness indexes of several welding joints are output. When the firmness index of the welding joint is 0, it means that the firmness of the welding joint is abnormal. When the firmness index of the welding joint is 1, it means that the firmness of the welding joint is normal.

4. A welding joint firmness detection system according to claim 3, characterized in that: The first firmness index is determined according to the welding pre-parameters, and the specific determination method is as follows: The welding pre-parameters include several characteristic parameters of their own state, and the characteristic parameters of the several self-states specifically reflect the quality of the layout before welding; The characteristic parameters of several self-states of several welded joints of the laid pipeline are compared with the design safety margins of several self-states of the laying process stored in the data warehouse. If the characteristic parameter of a certain self-state is not within the corresponding design safety margin, the abnormal value of the characteristic parameter of the self-state is recorded as 1. In this way, the abnormal values ​​of the characteristic parameters of several self-states of several welded joints of the laid pipeline are obtained, and the average values ​​are processed to obtain the first firmness index of the several welded joints of the laid pipeline.

5. A welding joint firmness detection system according to claim 3, characterized in that: The second firmness index is determined according to the welding process parameters, and the specific determination method is: The welding process parameters include characteristic parameters of several welding parameters, and the characteristic parameters of the several welding parameters specifically reflect the quality of the welding process; The characteristic parameters of a plurality of welding parameters of a plurality of welding joints of the laid pipeline are processed in the same manner to obtain second firmness indexes of the plurality of welding joints of the laid pipeline.

6. A welding joint firmness detection system according to claim 1, characterized in that: The execution of the ultrasonic phased array detection unit also includes: quickly performing three-dimensional modeling of the plurality of weld joints of the laid pipeline, and determining the scanning angles, focusing laws, and start and end chip parameters of the plurality of weld joints based on the three-dimensional model, specifically including the following: A stored welding joint model-ultrasonic phased array detection parameter mapping table is extracted from a data warehouse, and the three-dimensional models of several welding joints of the laid pipeline and several example three-dimensional models in the welding joint model-ultrasonic phased array detection parameter mapping table are imported into a model similarity assessment model. The similarity between the three-dimensional models of the several welding joints and the several example three-dimensional models is output, and the ultrasonic phased array detection parameters corresponding to the example three-dimensional model with the maximum similarity are selected as the ultrasonic phased array detection parameters of the welding joint. The ultrasonic phased array detection parameters include scanning angle, focal law, and start and end chip parameters.

7. A welding joint firmness detection system according to claim 1, characterized in that: The specific identification method of the automatic identification of potential defect sets is as follows: Obtain a displacement vector field based on the stress and deformation data of several welded joints of the laid pipeline, and calculate the strain field based on the displacement vector field to obtain the maximum principal strain ε1 field, the equivalent strain ε0q field, the displacement discontinuity D field, and the strain concentration factor K field. The stress and deformation data include images before and after deformation. Identify strain field features, traverse the defect type-strain field feature mapping table stored in the data warehouse, and output several potential defects of several weld joints of the laid pipeline; Based on the heat conduction data of several welded joints of the laid pipeline, which includes terahertz wave reflection signals in several regions, the temperature gradient abnormal regions of the several welded joints of the laid pipeline are identified, namely, potential abnormal regions.

8. A welding joint firmness detection system according to claim 7, characterized in that: The displacement vector field is specifically calculated from the images before and after deformation by using a correlation function, and reflects the overall deformation.

9. A welding joint firmness detection system according to claim 7, characterized in that: The identification of abnormal temperature gradient areas of several welding joints of the laid pipeline is specifically obtained by extracting several solder material data based on the terahertz wave reflection signal and several designed solder material data of the welding joints stored in the data warehouse.

10. A method for implementing the welding joint firmness detection system according to any one of claims 1 to 9, characterized in that: include: S1. Collecting welding parameter sets of the weld joints of the laid pipeline; S2. A set of welding parameters for the weld joints of the laid pipeline is generated to generate a set of weld joint firmness indexes for the laid pipeline. A determination is made based on the weld joint firmness index minus the firmness abnormality level to determine whether the weld joints of the laid pipeline have firmness abnormalities. If so, S3 is executed. S3. Driving an adaptive robot to automatically adapt to the inner wall of the pipeline by hydraulic or mechanical arm structure, the adaptive robot is provided with a retractable track and a modular detection module; S4. Classify and integrate multimodal inspection data, automatically identify visible defect sets and potential defect sets, and simultaneously generate weld joint firmness inspection reports.

Images