A small space steel structure welding and polishing integrated robot and a working method thereof

Abstract

The application belongs to the technical field of steel structure welding and polishing, and relates to a small-space steel structure welding and polishing integrated robot and a working method thereof. The working method comprises the following steps: acquiring a welding seam position list of a steel structure to be worked, space environment information, a current position of the robot and a remote issued work task instruction, and planning a collision-free moving track according to the above information; controlling the robot to move to a first target welding seam position according to the collision-free moving track; collecting a two-dimensional image of the first target welding seam and extracting a welding seam edge graph, and simultaneously scanning a welding seam area to generate corresponding three-dimensional point cloud data; identifying a welding seam type and extracting welding seam size parameters based on the welding seam edge graph and the three-dimensional point cloud data; determining an optimal welding track and corresponding welding process parameters, and starting welding work; in the welding process, continuously correcting a welding gun posture to make it always keep perpendicular to a welding seam surface normal, and dynamically adjusting welding process parameters according to a real-time monitored welding state.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of steel structure welding and polishing, and particularly relates to a small-space steel structure welding and polishing integrated robot and a working method thereof. BACKGROUND

[0002] In the narrow space of steel structures such as ship cabins, box beam cavities, and equipment foundation components, welding and post-weld polishing are common construction processes. However, due to the high degree of space closure and insufficient ventilation in such structures, high temperatures, smoke, and harmful gas accumulation often occur during operation, posing significant safety risks for workers who spend long periods in such environments. At the same time, the limited operating space restricts the range of movement of welding guns and polishing tools, often requiring workers to adopt uncomfortable postures to complete the work, affecting the stability of the operation and reducing overall work efficiency.

[0003] In addition, the components in the small space are arranged compactly, with many obstructions, making it difficult to approach the weld position, and the positioning and clamping of equipment are inconvenient, and the weld accessibility is poor. Under such conditions, defects such as incomplete fusion, slag inclusion, or porosity are more likely to occur during welding, and the distribution of welding heat input is not easy to maintain uniformity, thereby increasing the risk of weld deformation or excessive residual stress. At the same time, the space conditions also make quality detection difficult, with limited visual inspection angles, and conventional detection methods such as ultrasonic waves are not easy to implement, resulting in the need for off-line detection after welding, which cannot timely detect problems and adjust the process.

[0004] Currently, although some welding operations have begun to introduce robotic equipment, existing equipment is mainly used in open environments and lacks adaptability to space-limited scenarios. Large equipment is difficult to enter narrow sections, and the welding unit and polishing unit are often on different platforms, making it impossible to continuously complete the pre and post processes, and errors are easily accumulated during repeated positioning, affecting the final weld formation. At the same time, there is still a lack of mature and practical complete technology for weld recognition, three-dimensional morphology acquisition, trajectory generation, and process monitoring in complex structures.

[0005] In summary, how to achieve the integration, stabilization, and automation of welding and polishing processes in a small space, and solve the problems of poor equipment accessibility, difficult positioning, inconvenient quality monitoring, and insufficient forming stability, has become a technical problem that needs to be solved. SUMMARY

[0006] The present application aims at the problems of poor equipment accessibility, limited manual operation, difficult quality monitoring and low process connection efficiency in steel structure welding and polishing operations in small spaces, and proposes a small-space steel structure welding and polishing integrated robot and its working method, which integrates welding, polishing and multi-source perception units on a compact platform, realizes the automation of weld identification, three-dimensional topography acquisition, trajectory planning and posture control, can complete high-precision welding and post-weld polishing processing in limited environments, effectively improves the weld forming consistency and operation efficiency, and provides reliable support for automatic manufacturing and maintenance operations in complex structures.

[0007] In order to achieve the above purpose, the first aspect of the present application provides a small-space steel structure welding and polishing integrated working method, comprising:

[0008] Obtaining the weld position list of the steel structure to be operated, the space environment information, the current position of the welding and polishing integrated robot and the remote issued operation task instruction, and planning a collision-free movement trajectory accordingly;

[0009] Controlling the robot to move to the first target weld position according to the collision-free movement trajectory;

[0010] Collecting the two-dimensional image of the first target weld and extracting the weld edge graph, and scanning the weld area to generate corresponding three-dimensional point cloud data;

[0011] Identifying the weld type and extracting the weld size parameters based on the weld edge graph and three-dimensional point cloud data;

[0012] According to the weld type and weld size parameters, determining the optimal welding trajectory and its corresponding welding process parameters, and starting the welding operation;

[0013] During the welding process, continuously correcting the welding gun posture to keep it always perpendicular to the weld surface normal, and dynamically adjusting the welding process parameters according to the real-time monitored welding state;

[0014] The method of collecting the two-dimensional image of the first target weld and extracting the weld edge graph is:

[0015] Controlling the global vision camera to obtain the two-dimensional image of the first target weld and inputting it into the intelligent recognition module for feature fusion to generate a weld image with complete edges;

[0016] Performing multi-scale feature extraction and step-by-step spatial recovery on the weld image to obtain different types of image pixels;

[0017] Dividing the image pixels into weld area, base material area and background area, and extracting the weld boundary contour to generate the weld edge graph.

[0018] In some embodiments, the method for scanning the weld area to generate corresponding three-dimensional point cloud data is:

[0019] A laser profile sensor is used to project a laser beam onto the weld surface to form a laser stripe on the weld area;

[0020] The laser profile sensor is controlled to scan along the extension direction of the weld, and the built-in CMOS camera continuously captures multiple frames of laser stripe images during the scanning process, and locates the center points of the stripes in each frame of image;

[0021] Based on the principle of triangulation and the pre-calibrated internal and external parameters of the CMOS camera, the spatial coordinates of each stripe center point are solved to obtain a set of three-dimensional sampling point coordinates accumulated along the scanning direction of the weld surface;

[0022] The set of three-dimensional sampling point coordinates is subjected to coordinate conversion, registration and splicing processing to generate complete three-dimensional point cloud data covering the weld area.

[0023] In some embodiments, the method for extracting weld size parameters is:

[0024] Based on the obtained three-dimensional point cloud data of the weld, multiple cross-section positions are determined along the length direction of the weld at a preset fixed interval, and the corresponding point cloud profile is extracted at each cross-section position;

[0025] Curve fitting is performed for each point cloud profile, and the geometric size parameters of the weld at the corresponding cross-section are calculated based on the fitting results;

[0026] The geometric size parameters measured at each cross-section position are statistically processed to calculate the average, standard deviation, maximum and minimum values of each parameter to comprehensively describe the size characteristics of the weld.

[0027] In some embodiments, the method for generating an optimal welding trajectory is:

[0028] Based on the start point coordinates, end point coordinates and weld edge map of the weld, a number of feature points representing the geometric features of the weld are extracted, and control points used to describe the geometric shape of the weld center line are selected from the feature points to form a control point set;

[0029] A cubic Bezier curve is constructed according to the control point set, and the spatial position and curve shape of the Bezier curve are determined through the spatial coordinates of each control point;

[0030] The spatial position of the control points is adjusted iteratively to make the Bezier curve fit the actual center line of the weld, and a fitting curve of the weld center line is obtained;

[0031] The fitting curve is discretized at a preset sampling interval to generate a sequence of welding path points, and the spatial coordinates of each path point are recorded.

[0032] For each welding path point, the tangent direction of the fitting curve at the path point is calculated as the welding torch advancing direction, and the normal vector of the weld surface at the welding path point is solved as the welding torch pose reference in combination with the weld three-dimensional point cloud data, to constrain the direction and pose of the trajectory point;

[0033] Based on the spatial coordinates of the welding path point, the welding torch advancing direction and the welding torch pose reference, the corresponding joint angle parameters are solved through the inverse kinematics of the welding robot to map the path point to the robot motion;

[0034] The welding path point sequence and the corresponding joint angle parameters are integrated to form a complete welding trajectory, i.e. the optimal welding trajectory.

[0035] In some embodiments, the small-space steel structure welding and polishing integrated working method further comprises:

[0036] After welding is completed, a dynamic polishing trajectory is generated according to the weld surface forming state and the preset optimal polishing strategy, and a polishing robot is driven to perform polishing work according to the dynamic polishing trajectory;

[0037] During polishing, based on real-time feedback of polishing pressure and surface flatness, the grinding head feed amount is automatically corrected and the dynamic polishing trajectory is optimized until the weld surface meets the quality requirements;

[0038] After completing the current weld work, the robot is controlled to move to the next weld position according to the collision-free movement trajectory, and the work of all welds is completed in turn.

[0039] In a second aspect, the present application provides a small-space steel structure welding and polishing integrated robot for realizing the small-space steel structure welding and polishing integrated working method of the first aspect, comprising:

[0040] A mobile working platform;

[0041] A welding robot and a polishing robot symmetrically arranged on both sides of the top of the mobile working platform;

[0042] A vision sensing module, a function control module, an intelligent identification module and a pose control module arranged on the mobile working platform, wherein:

[0043] The vision sensing module is used to acquire visual information of the weld area;

[0044] The intelligent identification module identifies the weld type and position based on the acquired visual information, and generates corresponding welding or / and polishing work trajectory;

[0045] The function control module controls the motion execution process of the welding robot arm, the polishing robot arm and the mobile working platform based on the welding or / and polishing operation track.

[0046] The posture control module is used for correcting the operation posture of the mobile working platform and the robot arm end effector in real time according to the feedback results of the visual sensing module and the intelligent identification module.

[0047] In some embodiments, the visual sensing module comprises:

[0048] At least one global visual camera is used for collecting two-dimensional images of the weld;

[0049] At least one laser contour sensor is used for collecting three-dimensional topographic information of the weld.

[0050] In some embodiments, the welding robot arm end is configured with:

[0051] A miniature industrial camera is used for collecting real-time weld process images;

[0052] An arc length tracking sensor is used for monitoring the change of the welding arc length.

[0053] In some embodiments, the polishing robot arm end is integrated with:

[0054] A force sensor is used for real-time detection of polishing contact force;

[0055] A laser displacement sensor is used for detecting the flatness of the weld surface after polishing.

[0056] Compared with the prior art, the advantages and positive effects of the present application are:

[0057] (1) By using robots to replace manual entry into closed or semi-closed small space environment, the risk conditions such as high temperature, smoke and harmful gas exposure of operators can be effectively avoided, and the safety hidden danger existing in traditional manual welding and polishing operation can be completely eliminated, and the construction safety can be guaranteed from the source.

[0058] (2) The robot has compact overall size, can move flexibly in a restricted space with a width of only about 400mm, and is suitable for operation areas that cannot be accessed by traditional equipment or manually. The welding robot arm and the polishing robot arm in the scheme can work independently or cooperatively, and can undertake welding and post-processing tasks of multiple types of welds; the system simultaneously supports two modes of autonomous control and manual intervention, can quickly adjust the strategy in the presence of obstacles or weld state mutations, and improves the operation reliability and adaptability.

[0059] (3) The robot is externally equipped with a protective shell and necessary heat dissipation and dust removal structure, which can effectively shield the influence of dust, welding slag and high temperature environment on internal electronic and transmission elements, prolong the service life of the whole machine. The easily damaged parts such as the grinding head and the dust collecting box adopt a modular quick disassembly and assembly structure, which can be replaced in a short time, reducing the maintenance workload and the later use cost. BRIEF DESCRIPTION OF DRAWINGS

[0060] Figure 1 It is a whole structure schematic diagram of a small-space steel structure welding and grinding integrated robot in the embodiment of the application;

[0061] Figure 2 It is a top view of the small-space steel structure welding and grinding integrated robot after removing the top shell in the embodiment of the application;

[0062] Figure 3 It is a flow chart of the small-space steel structure welding and grinding integrated working method in the embodiment of the application.

[0063] In the figure: 1, a movement control module; 2, a function control module; 3, a wireless transmission module; 4, an intelligent identification module; 5, a posture control module; 6, an auxiliary system; 7, a visual sensing module; 8, a protective shell; 9, a rotating wheel; 10, a six-axis high-precision structure; 11, a welding device; 12, a miniature industrial camera; 13, a grinding head. DETAILED DESCRIPTION

[0064] In the following, the application will be specifically described through exemplary embodiments. However, it should be understood that the elements, structures and features in one embodiment can also be beneficially combined into other embodiments without further description.

[0065] The welding and grinding operation of steel structure in a narrow space is limited by the space size, ventilation condition and visual range, and problems such as equipment cannot reach, welding seam identification is difficult, operation posture is limited often occur, which leads to unstable welding seam forming quality, high rework rate and low overall construction efficiency. The existing operation mode still relies on manual observation, manual operation and experience judgment, and it is difficult to realize real-time acquisition of welding seam position and appearance, and it is also impossible to dynamically correct the welding and grinding process, which is easy to produce welding defects and uneven processing quality risks. The application proposes a small-space steel structure welding and grinding integrated robot and its working method, which realizes accurate acquisition of welding seam space characteristics and welding-grinding full-process automatic operation by integrating visual perception, three-dimensional scanning, path planning and posture control, can generate an operation record containing welding seam type, size parameter and dynamic adjustment information, and significantly improves the consistency and quality stability of welding seam processing.

[0066] In one broad embodiment of the application, a small-space steel structure welding and grinding integrated working method, comprising:

[0067] obtain a welding seam position list of a steel structure to be operated, spatial environment information, a current position of a welding and grinding integrated robot, and an operation task instruction issued remotely, and plan a collision-free movement trajectory based on the above information;

[0068] control the robot to move to a first target welding seam position according to the collision-free movement trajectory;

[0069] collect a two-dimensional image of the first target welding seam and extract a welding seam edge map, and scan the welding seam area to generate corresponding three-dimensional point cloud data;

[0070] identify the welding seam type and extract the welding seam size parameters based on the welding seam edge map and the three-dimensional point cloud data;

[0071] determine the optimal welding trajectory and the corresponding welding process parameters according to the welding seam type and the welding seam size parameters, and start the welding operation;

[0072] During the welding process, continuously correct the welding torch posture to keep it always perpendicular to the welding seam surface normal, and dynamically adjust the welding process parameters according to the real-time monitored welding state;

[0073] The method for collecting the two-dimensional image of the first target welding seam and extracting the welding seam edge map is as follows:

[0074] control the global vision camera to collect the two-dimensional image of the first target welding seam and input the intelligent recognition module 4 for feature fusion to generate a complete edge welding seam image;

[0075] perform multi-scale feature extraction and step-by-step spatial recovery on the welding seam image to obtain different types of image pixels;

[0076] divide the image pixels into a welding seam area, a base material area, and a background area, and extract a welding seam boundary contour to generate a welding seam edge map.

[0077] In some embodiments, the method for scanning the welding seam area to generate corresponding three-dimensional point cloud data is as follows:

[0078] project a laser beam onto the welding seam surface using a laser profile sensor to form a laser stripe in the welding seam area;

[0079] control the laser profile sensor to scan along the welding seam extension direction, and the built-in CMOS camera continuously collects multiple frames of laser stripe images during the scanning process and locates the stripe center points in each frame of image;

[0080] based on the triangulation principle and the pre-calibrated internal and external parameters of the CMOS camera, solve the spatial coordinates of each stripe center point to obtain a set of three-dimensional sampling point coordinates accumulated along the scanning direction of the welding seam surface;

[0081] The three-dimensional sampling point coordinate set is subjected to coordinate conversion, registration and splicing processing to generate complete three-dimensional point cloud data covering the weld area.

[0082] In some embodiments, the method for extracting weld size parameters is:

[0083] Based on the obtained weld three-dimensional point cloud data, a plurality of cross-section positions are determined along the length direction of the weld at a preset fixed interval, and a corresponding point cloud profile is extracted at each cross-section position;

[0084] Curve fitting is performed for each point cloud profile, and the geometric size parameters of the weld at the corresponding cross-section are calculated based on the fitting results;

[0085] The geometric size parameters measured at each cross-section position are statistically processed to calculate the average, standard deviation, maximum and minimum values of each parameter to comprehensively describe the size characteristics of the weld.

[0086] In some embodiments, the method for generating an optimal welding trajectory is:

[0087] Based on the start point coordinates, end point coordinates and weld edge map of the weld, a plurality of feature points representing the geometric characteristics of the weld are extracted, and control points used to describe the geometric shape of the weld center line are selected from the feature points to form a control point set;

[0088] A cubic Bezier curve is constructed according to the control point set, and the spatial position and curve shape of the Bezier curve are determined by the spatial coordinates of each control point;

[0089] The spatial position of the control points is adjusted iteratively to make the Bezier curve fit the actual center line of the weld, and a fitting curve of the weld center line is obtained;

[0090] The fitting curve is discretized at a preset sampling interval to generate a sequence of welding path points, and the spatial coordinates of each path point are recorded;

[0091] For each welding path point, the tangent direction of the fitting curve at the path point is calculated as the advancing direction of the welding torch, and the normal vector of the weld surface at the welding path point is solved based on the weld three-dimensional point cloud data as a reference for the welding torch posture to constrain the direction and posture of the path point;

[0092] Based on the spatial coordinates of the welding path points, the advancing direction of the welding torch and the reference for the welding torch posture, the corresponding joint angle parameters are solved through inverse kinematics of the welding robot to map the path points to the robot motion;

[0093] The sequence of welding path points and the corresponding joint angle parameters are integrated to form a complete welding trajectory, i.e. the optimal welding trajectory.

[0094] In some embodiments, the small-space steel structure welding and polishing integrated working method further comprises:

[0095] After the welding is completed, a dynamic polishing track is generated according to the surface forming state of the weld and a preset optimal polishing strategy, and a polishing mechanical arm is driven to perform polishing work according to the dynamic polishing track;

[0096] During the polishing process, the feed amount of the grinding head 13 is automatically corrected and the dynamic polishing track is optimized based on the real-time feedback of the polishing pressure and the surface flatness until the weld surface meets the quality requirements.

[0097] After the current weld work is completed, the robot is controlled to move to the next weld position according to a collision-free movement track, and the work of all welds is completed in turn.

[0098] The application also provides a small-space steel structure welding and polishing integrated robot for realizing the above-mentioned small-space steel structure welding and polishing integrated working method, comprising:

[0099] A mobile working platform;

[0100] Welding mechanical arms and polishing mechanical arms symmetrically arranged on both sides of the top of the mobile working platform;

[0101] A vision sensing module 7, a function control module 2, an intelligent identification module 4 and a posture control module 5 arranged on the mobile working platform, wherein:

[0102] The vision sensing module 7 is used to acquire visual information of the weld area;

[0103] The intelligent identification module 4 identifies the weld type and position based on the acquired visual information and generates corresponding welding or / and polishing work tracks;

[0104] The function control module 2 controls the movement of the welding mechanical arms, the polishing mechanical arms and the mobile working platform based on the welding or / and polishing work tracks;

[0105] The posture control module 5 is used to correct the working posture of the mobile working platform and the end effector of the mechanical arm in real time according to the feedback results of the vision sensing module 7 and the intelligent identification module 4.

[0106] In some embodiments, the vision sensing module 7 comprises:

[0107] At least one global vision camera for collecting two-dimensional images of the weld;

[0108] And at least one laser profile sensor for collecting three-dimensional topographic information of the weld.

[0109] In some embodiments, the welding robot arm is configured with:

[0110] a miniature industrial camera 12 for real-time acquisition of weld seam welding process images;

[0111] and an arc length tracking sensor for monitoring changes in the length of the welding arc.

[0112] In some embodiments, the polishing robot arm is integrated with:

[0113] a force sensor for real-time detection of polishing contact force;

[0114] and a laser displacement sensor for detecting the flatness of the weld seam surface after polishing.

[0115] The embodiments of the present application will be described in detail below with reference to the accompanying drawings.

[0116] Referring to Figure 1 and Figure 2 , the first aspect of the present application provides a small space steel structure welding and polishing integrated robot, in order to meet the small space through capacity demand, its overall size design is about long x wide x high = 800 mm x 400 mm x 500 mm, including a mobile work platform, a welding robot arm and a polishing robot arm, the welding robot arm and the polishing robot arm are symmetrically installed on the top of the mobile work platform on both sides, and are fixed with the internal steel structure of the mobile work platform through high-strength bolts; the base of the polishing robot arm and the welding robot arm is provided with a rotary joint, which can realize 360° horizontal rotation, thereby expanding the working range.

[0117] The mobile work platform includes a vision sensing module 7, a function control module 2, an intelligent identification module 4 and a posture control module 5, wherein:

[0118] The vision sensing module 7 is used to obtain visual information of the seam area, including two high-definition global vision cameras and a laser profile sensor. The global vision camera is used to shoot two-dimensional images of the weld seam, and the laser profile sensor is used to scan three-dimensional topographic information of the weld seam. The collected two-dimensional images and three-dimensional shape data are transmitted to the intelligent identification module 4 for subsequent weld seam identification and path planning.

[0119] The function control module 2 coordinates and controls the motion execution process of the welding robot arm, the polishing robot arm and the mobile work platform based on the welding or / and polishing operation trajectory. It adopts a PLC controller with sixteen digital input / output interfaces for receiving manual instructions or signals from the intelligent identification module 4 and outputting control signals to the welding device 11 and the polishing tool system to realize the switching of the working mode. At the same time, the module also coordinates the posture of the robot arm and the motion of the mobile work platform to ensure the collaborative work of each component.

[0120] The intelligent recognition module 4 identifies the type and location of the weld based on the collected visual information and generates the corresponding welding or / and polishing track. It has a built-in weld recognition algorithm based on a deep learning model and a path planning algorithm. After receiving the two-dimensional image and three-dimensional shape data from the visual sensing module 7, the deep learning model can identify the type of weld (such as fillet weld, butt weld), size (such as weld leg height, weld width), and then plan a collision-free track, and further plan the optimal welding / polishing track.

[0121] The posture control module 5 is used to correct the working posture of the mobile working platform and the end effector of the robot in real time according to the feedback results of the visual sensing module 7 and the intelligent recognition module 4. The posture control module 5 includes a six-axis gyroscope and a servo drive unit. The gyroscope collects the tilt angle data of the robot in real time. If the tilt exceeds the preset threshold, it outputs a signal to the height adjustment mechanism (built-in electric push rod, adjustment stroke 0-50mm) of the rotating wheel 9 to adjust to horizontal. At the same time, the module controls the joint angle of the robot according to the three-dimensional profile of the weld to ensure that the welding / polishing tool is perpendicular to the weld surface.

[0122] The welding robot adopts a six-axis high-precision structure 10, and each axis uses a harmonic reducer to meet the posture adjustment requirements of complex welds. A miniature industrial camera 12 is installed at the end of the welding robot (near the welding gun) to collect images of the welding process in real time and transmit them to the remote control end. The welding device 11 uses a metal inert gas (MIG) welding system that can automatically match the welding parameters according to the weld thickness (2-10mm). At the same time, an arc length tracking sensor is built in to monitor the change of the welding arc length, which can adjust the height of the welding gun in real time to avoid welding defects caused by changes in weld height.

[0123] The polishing robot also adopts a six-axis high-precision structure 10 to meet the polishing track following requirements under complex weld topography. The polishing robot end is integrated with a polishing tool system, which consists of a replaceable grinding head 13, a high-speed drive motor, a feed adjustment mechanism, and a state detection unit. The grinding head 13 adopts a modular structure and can quickly switch between grinding wheel pieces (for rough grinding) and louver wheels (for fine grinding) according to process requirements. The high-speed motor provides stable output speed for the grinding head 13, and the feed amount is accurately adjusted by the micro-feeding mechanism driven by the servo motor to adapt to different weld heights and surface unevenness. A force sensor is installed between the grinding head 13 and the robot end to detect the polishing contact force in real time and feedback to the function control module 2, realizing closed-loop adjustment of the grinding head 13 feed amount to avoid over-polishing or under-polishing. At the same time, the polishing tool system also integrates a laser displacement sensor to detect the flatness of the polished weld surface, providing data support for subsequent quality judgment.

[0124] The small-space steel structure welding and polishing integrated robot provided by the application realizes automatic identification of a welding seam, welding and polishing full-process processing, and changes traditional manual experience-based operation into data-based accurate control through compact platform design, double-robot arm collaborative operation and multi-source visual perception. The robot can flexibly pass through a limited space with a width of about 400 mm, replaces manual operation into a high-temperature, dust and harmful gas environment, and effectively eliminates the safety risk of narrow-space operation. The identification algorithm based on deep learning and the real-time posture regulation mechanism ensure that the welding forming and polishing flatness are highly consistent under the condition of a complex welding seam, significantly reduce the rework amount and improve the quality stability. The modular polishing head, replaceable wear parts and external protective structure further reduce the maintenance cost and ensure long-term stable operation in a closed, dusty and high-temperature environment.

[0125] Referring to Figure 1 and Figure 2 , the second aspect embodiment of the application provides a small-space steel structure welding and polishing integrated robot, the mobile working platform further comprises a mobile control module 1, a wireless transmission module 3, an auxiliary system 6, a protective shell 8 and four rotating wheels 9 for movement, wherein:

[0126] The core chip of the mobile control module 1 is built-in PID algorithm, the response time is less than or equal to 100 ms, and the mobile control module 1 is used for controlling the robot movement track. The module receives spatial coordinate data, combines a preset route, adjusts the rotating speed of the rotating wheel 9 through the PID algorithm, compensates the movement error, and realizes accurate positioning.

[0127] The wireless transmission module 3 adopts 5G / 4G dual-mode communication, the transmission rate is greater than or equal to 100 Mbps, and the delay is less than or equal to 50 ms. The module is used for transmitting the visual data of the visual sensing module 7, the pressure data of the force sensor and the real-time temperature data of the temperature sensor to a remote control end (computer / tablet), and simultaneously receiving the control instructions (such as route adjustment and parameter modification) of the remote control end, so as to realize bidirectional data interaction between the robot and the remote control end.

[0128] The auxiliary system 6 comprises a cooling fan, a temperature sensor and a dust removal fan, the temperature sensor is used for monitoring the internal temperature of the platform, the cooling fan is automatically started when the temperature is greater than 60 DEG C, the dust removal fan continuously operates during the welding and polishing process, dust and welding slag are sucked into the built-in dust collection box through a pipeline, and meanwhile, a cooling water pipeline is arranged near the welding device 11 and is used for real-time cooling of a welding gun nozzle.

[0129] The protective shell 8 adopts 304 stainless steel with a thickness of 3 mm, and a high-temperature-resistant coating is sprayed on the surface, the shell is in a sealed structure, sealing rubber strips are arranged at key positions (such as wiring ports and motors), and dust screens are arranged only at the cooling fan and the dust removal fan; the welding robot arm, the polishing robot arm and the platform connection part adopt telescopic dust covers to prevent welding slag from entering the joint gap.

[0130] The small-space steel structure welding and polishing integrated robot provided by the application has the advantages that the stable support and efficient cooperation of welding and polishing operations in a limited space are realized through the precise trajectory adjustment of the movement control module 1, the high-speed data interaction of the wireless transmission module 3 and the intelligent temperature control and dust removal of the auxiliary system 6. The positioning accuracy is significantly improved by the motion control driven by the PID algorithm, so that the robot can maintain reliable mobility in a narrow environment; the real-time return of visual and sensing data is guaranteed by 5G / 4G communication, and the remote scheduling capability is strengthened; the perfect heat dissipation, dust removal and cooling structure avoids performance degradation caused by temperature rise or dust accumulation. The sealing protective shell 8 combined with the telescopic dust cover effectively blocks the welding slag and dust from entering the key parts, and improves the durability of the whole machine. The overall structure makes the robot have high stability, high reliability and low maintenance requirement in the welding and polishing integrated operation, and provides an efficient and safe automatic solution for small-space steel structure processing.

[0131] Referring to Figure 3 The third aspect of the application provides a small-space steel structure welding and polishing integrated working method, which is applied to the small-space steel structure welding and polishing integrated robot of the second aspect of the application and includes the following steps.

[0132] Step 1: Obtain the welding seam position list of the steel structure to be operated, the space environment information, the current position of the welding and polishing integrated robot and the operation task instruction issued remotely, and plan a collision-free movement trajectory based on the above information.

[0133] Specifically, the method for obtaining the welding seam position list of the steel structure to be operated is as follows:

[0134] A plurality of spatial positioning reference points with unique coded marks are arranged in the operation area;

[0135] The spatial distances between the reference points are measured, and a field coordinate system describing the actual structure on site is generated based on the measured spatial distances;

[0136] The spatial registration of the digital model of the steel structure is performed based on the field coordinate system, so that the digital model coordinates and the field coordinate reference are kept consistent;

[0137] The theoretical coordinates of each welding seam are extracted from the registered digital model of the steel structure, and are converted into corresponding field coordinates;

[0138] The welding seams are prioritized according to their spatial positions and preset operation strategies, and then a welding seam position list containing the welding seam position and attribute information is formed.

[0139] Specifically, the method for obtaining the space environment information is as follows:

[0140] The mobile work platform is controlled to move along a preset path in a work area, a laser profile sensor is used to continuously scan a steel structure component, a support frame, a pipeline equipment and other obstacles affecting work, and spatial environment data of the work area is acquired;

[0141] During the scanning process, a visual texture image of the work area is synchronously acquired by a global vision camera, which is used to supplement surface feature and spatial boundary information of the obstacles;

[0142] The spatial environment data and the visual texture image are spatially registered and fused to construct a three-dimensional environment map containing geometric structure, surface texture and spatial relationship;

[0143] In the three-dimensional environment map, the position and shape of a static obstacle are identified and labeled, and a safety boundary of a dangerous area is demarcated according to a work rule, a minimum width of a passing path is evaluated, and a movement freedom degree constraint condition of a mechanical arm at different positions is determined.

[0144] Step 2, the robot is controlled to move to a first target weld position according to a collision-free movement trajectory.

[0145] Step 3, a two-dimensional image of the first target weld is acquired and a weld edge map is extracted, and the weld area is scanned to generate corresponding three-dimensional point cloud data.

[0146] Specifically, the method for acquiring the two-dimensional image of the first target weld and extracting the weld edge map is as follows:

[0147] The global vision camera is controlled to acquire the two-dimensional image of the first target weld and input the intelligent recognition module 4 for feature fusion to generate a weld image with complete edges;

[0148] Multi-scale feature extraction and step-by-step spatial recovery are performed on the weld image to obtain different types of image pixels;

[0149] The image pixels are divided into a weld area, a base material area and a background area, and a weld boundary contour is extracted to generate a weld edge map.

[0150] Specifically, the method for scanning the weld area to generate corresponding three-dimensional point cloud data is as follows:

[0151] A laser profile sensor is used to project a laser beam onto the weld surface to form a laser stripe in the weld area;

[0152] The laser profile sensor is controlled to scan along the extension direction of the weld, and a built-in CMOS camera continuously acquires multiple frames of laser stripe images during the scanning process, and the center points of the stripes in each frame of image are located;

[0153] Based on the principle of triangulation and the pre-calibrated internal and external parameters of the CMOS camera, the spatial coordinates of each fringe center point are solved to obtain a set of three-dimensional sampling point coordinates accumulated along the scanning direction of the weld surface;

[0154] The set of three-dimensional sampling point coordinates is subjected to coordinate conversion, registration and splicing processing to generate complete three-dimensional point cloud data covering the weld area.

[0155] Step 4, based on the weld edge map and the three-dimensional point cloud data, the weld type is identified and the weld size parameters are extracted.

[0156] Specifically, the method for extracting weld size parameters is:

[0157] Based on the obtained three-dimensional point cloud data of the weld, a plurality of cross-section positions are determined along the length direction of the weld at a preset fixed interval, and a corresponding point cloud profile is extracted at each cross-section position;

[0158] Curve fitting is performed for each point cloud profile, and the geometric size parameters of the weld at the corresponding cross-section are calculated based on the fitting results;

[0159] The geometric size parameters measured at each cross-section position are statistically processed to calculate the average, standard deviation, maximum and minimum values of each parameter to comprehensively describe the size characteristics of the weld.

[0160] Specifically, the method for generating the optimal welding trajectory is:

[0161] Based on the start point coordinates, end point coordinates and weld edge map of the weld, a plurality of feature points representing the geometric features of the weld are extracted, and control points used to describe the geometric shape of the weld center line are selected from the feature points to form a control point set;

[0162] A cubic Bezier curve is constructed according to the control point set, and the spatial position and curve shape of the Bezier curve are determined by the spatial coordinates of each control point;

[0163] The spatial position of the control points is adjusted iteratively to make the Bezier curve fit the actual center line of the weld, and a fitting curve of the weld center line is obtained;

[0164] The fitting curve is discretized at a preset sampling interval to generate a sequence of welding path points, and the spatial coordinates of each path point are recorded;

[0165] For each welding path point, the tangent direction of the fitting curve at the path point is calculated as the advancing direction of the welding torch, and the normal vector of the weld surface at the welding path point is solved based on the three-dimensional point cloud data of the weld, which is used as a reference for the welding torch attitude to constrain the direction and attitude of the path point.

[0166] Based on the spatial coordinates of the welding path points, the welding torch advancing direction, and the welding torch posture reference, the corresponding joint angle parameters are solved through the inverse kinematics of the welding robot arm to map the path points to the robot arm motion;

[0167] The welding path point sequence and the corresponding joint angle parameters are integrated to form a complete welding trajectory, i.e., the optimal welding trajectory.

[0168] Step 5, according to the welding type and the welding size parameters, the optimal welding trajectory and its corresponding welding process parameters are determined, and the welding operation is started.

[0169] Step 6, during the welding process, the welding torch posture is continuously corrected to keep it always perpendicular to the weld surface normal, and the welding process parameters are dynamically adjusted according to the real-time monitored welding state.

[0170] Step 7, after the welding is completed, the dynamic polishing trajectory is generated according to the weld surface forming state and the preset optimal polishing strategy, and the polishing robot arm is driven to perform polishing operation according to the dynamic polishing trajectory.

[0171] Step 8, during the polishing process, based on the real-time feedback of polishing pressure and surface flatness, the grinding head 13 feed amount is automatically corrected and the dynamic polishing trajectory is optimized until the weld surface meets the quality requirements.

[0172] Specifically, the method for automatically correcting the grinding head 13 feed amount based on the real-time feedback of polishing pressure and surface flatness is:

[0173] The normal pressure of the grinding head 13 in the direction perpendicular to the workpiece surface and the tangential friction along the workpiece surface are collected in real time, and the actual contact pressure in the polishing process is obtained accordingly;

[0174] The profile information of the surface in the area in front of the movement direction of the grinding head 13 is synchronously acquired to obtain the surface height variation trend of the area to be reached by the grinding head 13;

[0175] The actual contact pressure and the surface height variation trend are fused to obtain comprehensive polishing state information for pressure stability judgment;

[0176] Based on the comprehensive polishing state information, pressure deviation judgment is performed, and when it is judged that the actual contact pressure deviates from the preset pressure value, the polishing robot arm is controlled to finely adjust the grinding head 13 pose or feed amount to compensate for the pressure deviation.

[0177] Specifically, the method for judging whether the weld surface meets the quality requirements is:

[0178] The polished weld surface is scanned again to obtain three-dimensional topographic point cloud data after polishing;

[0179] The three-dimensional topography data after polishing is compared and analyzed with the topography data before polishing to calculate the actual removal amount of the weld reinforcement, the surface flatness deviation, and whether there is a concave area caused by over-polishing;

[0180] A high-resolution gray-scale image of the weld surface is collected, and the directionality, uniformity and scratch depth parameters of the surface texture are extracted by the intelligent recognition module 4;

[0181] The measured geometric size parameters and surface quality parameters are automatically compared with the preset quality acceptance standard: when all detection indexes are in the qualified interval, it is determined that the weld surface polishing quality is qualified; if any index exceeds the tolerance range, a repair instruction containing the defect position and type is automatically generated, and the polishing robot is guided to perform targeted supplementary polishing operation.

[0182] Step 9, after completing the current weld operation, the robot moves to the next weld position according to the collision-free movement trajectory, and completes the operation of all welds in turn.

[0183] The above-mentioned small space steel structure welding and polishing integrated working method of the application realizes high automation and fine control of the whole process of welding and polishing through weld position list extraction, three-dimensional environment modeling, collision-free path planning, weld feature recognition, optimal welding trajectory generation and real-time posture correction. The weld recognition mechanism based on three-dimensional point cloud and visual feature fusion significantly improves the accuracy of weld positioning and size extraction; the Bezier curve fitting combined with inverse kinematics solving ensures the continuity and posture consistency of the welding trajectory; the real-time feedback regulation mechanism in the welding and polishing stages effectively suppresses the process instability caused by posture deviation, pressure fluctuation or surface height change. With the high mobility of the robot in the restricted space, this method not only ensures the weld forming quality, but also significantly reduces the degree of artificial intervention, improves the operation efficiency and stability, and provides a reliable technical path for the automatic construction of complex steel structures.

[0184] The above examples are used to explain the application, but not to limit the application, any modifications and changes made to the application within the spirit and protection scope of the claims fall within the protection scope of the application.

Claims

1. A method for integrated welding and grinding of steel structures in small spaces, characterized in that, include: The system obtains a list of weld locations on the steel structure to be worked, spatial environment information, the current position of the integrated welding and grinding robot, and remotely issued work instructions, and plans a collision-free movement trajectory accordingly. The robot is controlled to move to the first target weld position according to a collision-free movement trajectory. Two-dimensional images of the first target weld are acquired and weld edge maps are extracted. At the same time, the weld area is scanned to generate corresponding three-dimensional point cloud data. Weld type identification and weld size parameters extraction based on weld edge map and 3D point cloud data; Based on the weld type and weld size parameters, determine the optimal welding trajectory and its corresponding welding process parameters, and start the welding operation; During the welding process, the welding torch posture is continuously corrected to keep it perpendicular to the normal of the weld surface, and the welding process parameters are dynamically adjusted according to the welding status monitored in real time. The method for acquiring a two-dimensional image of the first target weld and extracting the weld edge image is as follows: The global vision camera is controlled to acquire a two-dimensional image of the first target weld and input into the intelligent recognition module for feature fusion to generate a weld image with complete edges; Multi-scale feature extraction and stepwise spatial reconstruction are performed on weld seam images to obtain different types of image pixels; The image pixels are divided into weld area, base material area and background area, and the weld boundary contour is extracted to generate weld edge map; The method for scanning the weld area to generate corresponding 3D point cloud data is as follows: A laser beam is projected onto the weld surface using a laser profile sensor to form laser stripes in the weld area; The laser contour sensor is controlled to scan along the extension direction of the weld seam. Its built-in CMOS camera continuously acquires multiple frames of laser stripe images during the scanning process and locates the center point of the stripes in each frame. Based on the principle of triangulation and the pre-calibrated internal and external parameters of the CMOS camera, the spatial coordinates of each stripe center point are solved to obtain the set of three-dimensional sampling point coordinates accumulated along the scanning direction on the weld surface. The coordinates of the three-dimensional sampling points are transformed, registered and stitched to generate complete three-dimensional point cloud data covering the weld area. The method for extracting weld size parameters is as follows: Based on the acquired 3D point cloud data of the weld, multiple cross-sectional positions are determined along the length of the weld at a preset fixed interval, and the corresponding point cloud contour is extracted at each cross-sectional position. For each point cloud contour, perform curve fitting, and calculate the geometric dimension parameters of the weld at the corresponding cross section based on the fitting results; The geometric dimensional parameters measured at each cross-sectional location are statistically processed to calculate the average, standard deviation, maximum and minimum values ​​of each parameter in order to comprehensively describe the dimensional characteristics of the weld. The method for generating the optimal welding trajectory is as follows: Based on the start coordinates, end coordinates, and edge diagram of the weld, several feature points characterizing the geometric features of the weld are extracted, and control points for describing the geometric shape of the weld centerline are selected from the feature points to form a control point set. A cubic Bézier curve is constructed based on the set of control points, and the spatial position and curve shape of the Bézier curve are determined by the spatial coordinates of each control point. By iteratively adjusting the spatial position of the control points, the Bezier curve is fitted to the actual centerline of the weld, thus obtaining the fitted curve of the weld centerline. The fitted curve is discretized at a preset sampling interval to generate a welding path point sequence, and the spatial coordinates of each path point are recorded. For each welding path point, the tangent direction of the fitted curve at that path point is calculated as the direction of the welding torch forward. Combined with the three-dimensional point cloud data of the weld, the normal vector of the weld surface at that welding path point is solved as a reference for the welding torch attitude, so as to constrain the direction and attitude of the trajectory point. Based on the spatial coordinates of the welding path points, the forward direction of the welding torch, and the welding torch posture reference, the corresponding joint angle parameters are solved through the inverse kinematics of the welding robot arm to map the path points to the robot arm movements. The welding path point sequence is integrated with the corresponding joint angle parameters to form a complete welding trajectory, i.e., the optimal welding trajectory.

2. The integrated welding and grinding method for small-space steel structures according to claim 1, characterized in that, Also includes: After welding is completed, a dynamic grinding trajectory is generated based on the surface formation of the weld and the preset optimal grinding strategy, and the grinding robot arm is driven to perform grinding operations according to the dynamic grinding trajectory. During the grinding process, based on real-time feedback of grinding pressure and surface flatness, the feed rate of the grinding head is automatically corrected and the dynamic grinding trajectory is optimized until the weld surface meets the quality requirements. After completing the current weld, the robot moves to the next weld position along a collision-free trajectory, and completes the work on all welds in sequence.

3. A small-space steel structure welding and grinding integrated robot, used to realize the small-space steel structure welding and grinding integrated working method as described in claim 2, characterized in that, include: Mobile work platform; The welding robotic arm and the grinding robotic arm are symmetrically arranged on both sides of the top of the mobile work platform; The visual sensing module, function control module, intelligent recognition module, and posture control module are installed on the mobile work platform, wherein: The visual sensing module is used to acquire visual information about the seam area; The intelligent recognition module identifies the weld type and location based on the collected visual information and generates corresponding welding and / or grinding operation trajectories. The functional control module coordinates and controls the motion execution process of the welding robot arm, the grinding robot arm and the mobile work platform based on the welding and / or grinding operation trajectory. The attitude control module is used to correct the working attitude of the mobile work platform and the end effector of the robotic arm in real time based on the feedback results of the vision sensing module and the intelligent recognition module.

4. The integrated welding and grinding robot for small-space steel structures according to claim 3, characterized in that, The visual sensing module includes: At least one global vision camera is used to acquire two-dimensional images of the weld. In addition, at least one laser profile sensor is used to acquire three-dimensional topographic information of the weld.

5. The integrated welding and grinding robot for small-space steel structures according to claim 4, characterized in that, The welding robotic arm is equipped with: Miniature industrial cameras are used to acquire images of the welding process in real time. In addition, an arc length tracking sensor is used to monitor changes in the welding arc length.

6. The integrated welding and grinding robot for small-space steel structures according to claim 4, characterized in that, The end of the grinding robotic arm integrates: Force sensors are used to detect grinding contact force in real time; In addition, a laser displacement sensor is used to detect the flatness of the weld surface after grinding.

Images