Steel structure factory building node connecting method based on artificial intelligence

Abstract

The invention relates to an artificial intelligence-based steel structure factory building node connection method, which comprises the following steps of: prefabricating various standardized module connecting pieces according to the design specification of a steel structure factory building; in a construction site, adaptive module connecting pieces are selected by utilizing an artificial intelligence technology according to nodes with different positions and specification requirements; performing preliminary butt joint on the module connecting piece and the steel structural member, so that connecting interfaces are aligned with each other; the module connecting piece and the steel structural member which are in butt joint are locked through a rapid locking device, and joint connection is completed; and the connection nodes are checked and reinforced, so that the stability and reliability of connection are ensured. According to the technical scheme, various standardized module connecting pieces are prefabricated, the adaptive module connecting pieces are selected through the artificial intelligence technology, and the connecting efficiency of the steel structure factory building joints is improved.

Description

Technical Field

[0001] The present disclosure relates to the technical field of steel structures, and particularly to a method for connecting nodes of a steel structure factory building based on artificial intelligence. Background Art

[0002] In the field of steel structure factory building construction, traditional node connection methods have many drawbacks. Lack of standardized and modular design, it is difficult to quickly adapt to the diverse requirements of factory building specifications, which is not conducive to large-scale and high-efficiency industrialized construction. Summary of the Invention

[0003] To overcome the problems existing in the related art, the present disclosure provides a method for connecting nodes of a steel structure factory building based on artificial intelligence to solve the problem of low working efficiency of node connection in the steel structure factory building in the related art.

[0004] According to the first aspect of the embodiments of the present disclosure, a method for connecting nodes of a steel structure factory building based on artificial intelligence is provided, including: Preparing a variety of standardized modular connectors according to the design specifications of the steel structure factory building; At the construction site, for nodes with different positions and specification requirements, using artificial intelligence technology to select suitable modular connectors; Performing a preliminary docking of the modular connectors with the steel structure members to align the connection interfaces with each other; Locking the docked modular connectors and steel structure members through a quick locking device to complete the node connection; Inspecting and strengthening the connection nodes to improve the stability and reliability of the connection.

[0005] In one embodiment, the modular connectors are made of high-strength alloy steel, formed by precision casting or machining, and the surface is treated with anti-corrosion.

[0006] In one embodiment, in the step of using artificial intelligence technology to select suitable modular connectors, a digital design software with an artificial intelligence model is used for node simulation analysis to quickly determine the type and quantity of the required modular connectors.

[0007] In one embodiment, in the step of using artificial intelligence technology to select suitable modular connectors, using a digital design software with a machine learning algorithm model for node simulation analysis, and quickly determining the type and quantity of the required modular connectors includes: Steps of data preparation and feature engineering, including: Collecting data, the data includes: the force condition of the node, geometric dimensions, material properties, and problem types, and the type and quantity of successfully matched connectors; Feature extraction and processing: Clean the original data and handle missing values and outliers; Numericalize the features, including: normalizing or standardizing continuous features of geometric dimensions and force conditions; Steps for model training, specifically including: Select a machine learning algorithm model; Divide the dataset and divide the prepared data into a training set, a validation set, and a test set; Use the training set to train the machine learning algorithm model. During the training process, monitor the performance of the machine learning algorithm model through the validation set to prevent overfitting; When the performance of the machine learning algorithm model on the validation set reaches the optimum, stop training; Steps for model evaluation, specifically including: Use the test set to evaluate the trained machine learning algorithm model and calculate the accuracy rate and mean square error; For the prediction of the connector type, the accuracy rate is an indicator to measure the correctness of the model prediction; for the prediction of the number of connectors, the mean square error can measure the deviation degree between the predicted value and the true value.

[0008] In one implementation, the connection interface includes bolt holes, card slots, or tenons, and the modular connector is connected to the steel structure member by means of bolts, snap connections, or mortise and tenon joints.

[0009] In some embodiments, in a large industrial plant construction project, a complex steel structure framework needs to be built. Modular connectors are selected to connect the steel structure members, and their interface forms are diverse, including bolt holes, card slots, and tenons, and the connection methods are bolt snap connections and mortise and tenon joints.

[0010] For steel structure members, Q345B hot-rolled H-beams are mainly used as steel columns and steel beams. The steel column specification is HW400×400×13×21, and the steel beam specification is HN300×150×6.5×9. These members are prefabricated in the factory and transported to the construction site.

[0011] The modular connector is customized according to the connection requirements of the steel structure member and is made of Q345B steel of the same material as the steel structure member. Bolt holes with a diameter of 22 mm are provided on the connector for connection with the corresponding bolt holes on the steel structure member through M20 high-strength bolts; the card slot is designed to be 100 mm long, 30 mm wide, and 10 mm deep and is matched with the card block on the steel beam flange; the tenon size is 50×50×80 mm (length×width×height) and is precisely matched with the mortise eye reserved on the steel column.

[0012] Column-beam connection (bolt clamping): At the connection node of the steel column and the steel beam, first preliminarily clamp and position the module connector with the clamping block on the flange of the steel beam through the card slot, align the bolt holes on the module connector with the bolt holes on the steel column, and insert the M20 high-strength bolts. Use a torque wrench to tighten according to the designed torque value of 80 N·m to ensure firm connection. After the bolts are tightened, mark them to prevent omission and loosening.

[0013] Steel beam splicing (tenon-mortise fit): For steel beams that need to be spliced due to insufficient length, tenon-mortise fit connection is adopted at the splicing location. Align the tenon at the end of one steel beam with the mortise at the end of the other steel beam and slowly push it in to make them fit tightly. To enhance the connection strength, weld a fillet weld with a height of 6 mm around the tenon-mortise connection. After welding, conduct appearance inspection and flaw detection to ensure the welding quality.

[0014] During the construction process, for each completed connection, the inspection personnel randomly check the torque value of the bolt connection and conduct an appearance inspection on the fit of the tenon-mortise connection and the card slot connection to ensure that the connection is tight without looseness or misalignment.

[0015] After the steel structure framework is erected, use a total station to measure the verticality and flatness of the overall structure, and control all deviations within the allowable range of the specifications, ensuring the stability and safety of the steel structure of the factory building and meeting the requirements of subsequent construction and use.

[0016] In one embodiment, the quick locking device is a hydraulic quick clamp, a pneumatic lock or a mechanical quick locking mechanism.

[0017] In this embodiment, the hydraulic quick clamp includes a lever-type hydraulic clamp, which utilizes the lever principle to amplify the force generated by the hydraulic pressure to achieve quick clamping, and is commonly used for the temporary fixation and docking of steel structure components.

[0018] The wedge-type hydraulic clamp drives the wedge through hydraulic pressure to generate a powerful clamping force, has high clamping accuracy and stability, and is suitable for steel structure nodes with high connection accuracy requirements.

[0019] The pneumatic lock includes a piston-type pneumatic lock. The piston-type pneumatic lock uses compressed air to drive the piston to achieve quick locking and release, has a fast response speed, and is commonly used for steel structure connection parts that need to be frequently loaded and unloaded.

[0020] The vane-type pneumatic lock drives the vane to rotate through compressed air, driving the locking mechanism to act, and has the characteristics of a compact structure and a small volume, and is suitable for steel structure installation scenarios with limited space.

[0021] Mechanical quick-locking mechanism, including eccentric-wheel quick-locking mechanism. The eccentric-wheel quick-locking mechanism realizes clamping and loosening by the rotation of the eccentric wheel, with simple operation and fast clamping speed, and is applicable to the connection of steel structures with not particularly high requirements for clamping force.

[0022] Ball-type quick-locking mechanism. The ball-type quick-locking mechanism realizes locking by the rolling of balls in the tapered hole, has a self-locking function, can prevent accidental loosening to a certain extent, and is commonly used for the quick splicing of steel structure modules.

[0023] In one implementation, in the steps of inspecting and strengthening the connection node, an ultrasonic flaw detector and a torque wrench tool are used to check the quality of the connection part, and the weak links are strengthened by welding and adding auxiliary supports.

[0024] In this embodiment, for a large-scale logistics and warehousing center, the main steel structure has been used for many years. There is a recent plan for large-scale equipment upgrading, and it is necessary to ensure the stability of the steel structure. The maintenance team conducts a comprehensive inspection and strengthening work on the connection nodes.

[0025] The ultrasonic flaw detector checks the welds. The steel roof truss of the logistics and warehousing center is welded by a large number of steel beams. The staff uses an ultrasonic flaw detector to detect each key weld one by one. When inspecting the butt weld of the main steel beam with a span of 30 meters, the flaw detector moves uniformly along the weld at a spacing of 30 mm. Through waveform analysis, a linear defect about 40 mm long is found at a depth of 30 mm inside the weld, which is judged as incomplete penetration, seriously affecting the structural strength.

[0026] The torque wrench measures the bolt tightening degree. The shelves in the warehousing center are connected to the ground and walls with high-strength bolts. According to the torque value required by the design, the staff uses a torque wrench to conduct spot checks on the bolts. At the connection node between the shelf and the wall, it is found that the measured torque values of some M16 bolts are 20% lower than the standard, which will cause connection loosening and affect the stability of the shelf.

[0027] For the incomplete penetration weld found by flaw detection, first use a grinding wheel to grind out a U-shaped groove at the defective part, with a depth reaching the deepest part of the defect and a width convenient for welding operation. Select a matching E5015 electrode. Preheat the base metal to 150 °C before welding, and use the multi-layer and multi-pass welding process for welding. Strictly control the interlayer temperature during the welding process. After welding, perform post-weld heat treatment to eliminate welding stress. Conduct flaw detection again to confirm that the defect has been completely eliminated.

[0028] For bolts with insufficient torque, the staff use a torque wrench to re-tighten them according to the standard torque value. To prevent the bolts from loosening again, intermittent welding is used to reinforce the surface between the bolt head and the connecting piece. The length of the weld is 1 / 3 of the bolt circumference, and a section is welded every 120°. The welding height is 4 mm. After the reinforcement is completed, the joints are inspected again to ensure reliable connection. After this maintenance, the steel structure of the logistics and warehousing center meets the requirements of the upgrade and renovation, ensuring the safe operation of the subsequent equipment.

[0029] In one embodiment, the modular connector is provided with lifting lugs or handles for easy handling and installation, and the specification model and installation direction identification are marked on the surface.

[0030] In one embodiment, when initially docking the modular connector with the steel structure member, a positioning tooling is used to assist and improve the docking accuracy.

[0031] The technical solutions provided by the embodiments of the present disclosure may include the following beneficial effects: The technical solution of this application prefabricates a variety of standardized modular connectors and uses artificial intelligence technology to select the appropriate modular connectors, improving the connection efficiency of the joints of the steel structure workshop.

[0032] It should be understood that the above general description and the following detailed description are only exemplary and explanatory, and cannot limit the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] The accompanying drawings herein are incorporated into the specification and form a part of the specification, showing embodiments consistent with the present disclosure and used together with the specification to explain the principles of the present disclosure.

[0034] Figure 1 is a flowchart of a method for connecting joints of a steel structure workshop based on artificial intelligence shown according to an exemplary embodiment. DETAILED DESCRIPTION

[0035] Here, the exemplary embodiments will be described in detail, and the examples are shown in the drawings. When the following description refers to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present disclosure. On the contrary, they are only examples of devices and methods consistent with some aspects of the present disclosure as detailed in the appended claims.

[0036] It should be noted that all actions of obtaining signals, information, or data in this application are carried out on the premise of complying with the corresponding data protection regulations and policies of the country where the location is located and obtaining the authorization given by the owner of the corresponding device.

[0037] Based on this, the present application proposes a method for connecting steel structure factory building nodes based on artificial intelligence, including the following steps: In step S102, according to the design specifications of the steel structure factory building, a variety of standardized modular connectors are prefabricated.

[0038] Each modular connector has a specific shape, size and connection interface.

[0039] In step S104, at the construction site, for nodes with different positions and specification requirements, artificial intelligence technology is used to select suitable modular connectors.

[0040] In this embodiment, the artificial intelligence technology can adopt machine learning algorithms. Machine learning algorithms are used to select suitable modular connectors. Specifically, by collecting a large amount of data of existing connectors, the machine learning model is trained. After the machine learning model is trained, it can automatically identify and determine the modular connectors.

[0041] In step S106, the modular connector is initially docked with the steel structure member to align the connection interfaces with each other.

[0042] In step S108, through a quick locking device, the docked modular connector and the steel structure member are locked to complete the node connection.

[0043] In step S110, the connection nodes are inspected and reinforced to improve the stability and reliability of the connection.

[0044] The technical solution of the present application prefabricates a variety of standardized modular connectors and uses artificial intelligence technology to select suitable modular connectors, improving the connection efficiency of the steel structure factory building nodes.

[0045] In some embodiments, the modular connector is made of high-strength alloy steel, formed by precision casting or machining, and the surface is treated with anti-corrosion.

[0046] In some embodiments, in the step of using artificial intelligence technology to select suitable modular connectors, a digital design software with an artificial intelligence model is used for node simulation analysis to quickly determine the type and quantity of the required modular connectors.

[0047] In some embodiments, in the step of using artificial intelligence technology to select suitable modular connectors, using digital design software with a machine learning algorithm model for node simulation analysis to quickly determine the type and quantity of the required modular connectors includes: Steps of data preparation and feature engineering, including: Collecting data, the data includes: the force condition of the node, geometric dimensions, material properties and problem types, the type and quantity of successfully matched connectors; Feature extraction and processing: Clean the original data and handle missing values and outliers; Numericalize the features, including: normalizing or standardizing continuous features of geometric dimensions and force conditions; Steps of model training, specifically including: Select a machine learning algorithm model; Among them, the machine learning algorithm model can be a support vector machine model.

[0048] Divide the dataset, and divide the prepared data into a training set, a validation set, and a test set.

[0049] Use the training set to train the machine learning algorithm model. During the training process, monitor the performance of the machine learning algorithm model through the validation set to prevent overfitting.

[0050] When the performance of the machine learning algorithm model on the validation set reaches the optimum, stop the training.

[0051] Steps of model evaluation, specifically including: Use the test set to evaluate the trained machine learning algorithm model, and calculate the accuracy rate and mean square error; For the prediction of the connector type, the accuracy rate is an indicator to measure the correctness of the model prediction; for the prediction of the number of connectors, the mean square error can measure the deviation degree between the predicted value and the true value.

[0052] In some embodiments, the following is an example of using a support vector machine (SVM) to determine relevant information about the node connections of a steel structure workshop.

[0053] Model input features include: the type of steel structure workshop (such as heavy industrial workshop, light steel structure workshop, etc.). The load conditions in the area where the workshop is located (including wind load, snow load, etc.). The force conditions at the node (tensile force, compressive force, shear force, etc.). The material of the connecting members (such as different grades of steel). The form of the node (such as beam-column node, column base node, etc.).

[0054] When determining the connector type, assume there are three types: high-strength bolt connectors, welded connectors, and riveted connectors. After training with a large amount of data on known steel structure workshop parameters and the corresponding appropriate connector types, the SVM model will master the mapping relationship between different feature combinations and connector types.

[0055] For example, for heavy industrial plants located in areas with high wind loads, the forces at the beam-column joints are complex and mainly tensile and shear forces. The connecting components are made of high-strength steel. The model may predict that high-strength bolted connections are suitable because they are easy to install and can provide reliable connection strength to adapt to complex force conditions.

[0056] When determining the number of connectors, the SVM model can use the force magnitude at the node, the size and number of the connecting components, etc. as input features. For example, for a beam-column node that is subjected to large shear forces, the connecting components are two H-shaped steels. Through training data, the model learns that in this case, a certain number of high-strength bolts are needed to ensure the reliability of the connection. Assuming that according to previous data, such a node requires 10 high-strength bolt connectors, after learning this relationship, the model can predict the number of connectors required when encountering a new node with similar characteristics.

[0057] In practical applications, it is necessary to collect a large amount of accurate steel structure plant-related data to train the model to ensure the accuracy and reliability of the model prediction. At the same time, the model results need to be appropriately adjusted and verified in combination with actual engineering experience.

[0058] In some embodiments, the following is an embodiment of a SVM model related to steel structure factory building connections.

[0059] Data collection includes the following: Connection type, collect data on different types of connections, such as high-strength bolt connections, welded connections, riveted connections, etc.

[0060] Connector size, record the key size parameters of the connector, such as the diameter and length of the bolts, the length and height of the welds, etc.

[0061] Steel properties, including yield strength, tensile strength and other data of the steel used in the connectors.

[0062] The stress conditions of the connection nodes, such as the tension, pressure, shear force and other values ​​​​of the nodes, can be obtained through actual measurement or finite element analysis and other methods.

[0063] Damage conditions, recording whether the connector is damaged during actual use or testing, as well as the type (such as loose bolts, weld cracking, etc.) and degree of damage, are used as the target variables of the model.

[0064] During model training, the sorted data is input into the SVM model for training, so that the model can learn the relationship between various characteristics of the connector (connector type, size, steel performance, stress condition, etc.) and the damage condition. By adjusting the parameters of the model, the model can predict the damage possibility of the connector as accurately as possible.

[0065] Adjust and verify in combination with engineering practical experience. In actual engineering, environmental factors have an important impact on the performance of connectors. For example, in a humid environment, connectors are more prone to corrosion, thus affecting their load-bearing capacity. Based on this experience, for connectors in a humid environment, on the basis of the model prediction results, the assessment of their failure risk can be appropriately increased. Then, select some data of connectors in actual steel structure factories that have not participated in training for verification. For example, for a group of new high-strength bolt connection nodes, with their various characteristic data known, use the trained SVM model to predict their failure possibility. Then, verify the accuracy of the model prediction by regularly checking the actual situation of these nodes, such as observing whether there are signs of bolt loosening, whether there are cracks in the connection parts, etc. If it is found that the prediction result does not match the actual situation, it is necessary to analyze the reasons and adjust and optimize the model, such as considering more actual factors or re-screening and processing the data.

[0066] In some embodiments, the connection interface includes bolt holes, card slots or tenons, and the modular connector and the steel structure member are cooperatively connected by means of bolts, clamping or tenon and mortise.

[0067] In some embodiments, the quick locking device is a hydraulic quick clamp, a pneumatic lock or a mechanical quick locking mechanism, which can apply sufficient locking force in a short time.

[0068] In some embodiments, in the step of inspecting and strengthening the connection node, tools such as ultrasonic flaw detectors and torque wrenches are used to inspect the quality of the connection part, and the weak links are strengthened by means of welding, adding auxiliary supports, etc.

[0069] In some embodiments, the modular connector is provided with lifting lugs or handles for easy handling and installation, and the surface is marked with identification such as specification model and installation direction.

[0070] In this embodiment, the modular connector is made of high-strength alloy steel. To meet different handling and installation scenarios, lifting lugs and handles are respectively arranged on its opposite side surfaces. The lifting lug is made by forging process, in a U-shaped structure, with a smooth surface and no defects, and is connected to the connector body by full welding. The weld seam is uniform and full, and is ensured to be firmly connected through flaw detection. The size of the lifting lug has been strictly calculated. Its width is 50 mm and its thickness is 20 mm, and it can withstand a tensile force of at least 5 tons, which is sufficient to cope with the force during the lifting of the connector. The handle is formed by bending a rectangular tube and is covered with a layer of anti-slip rubber to increase friction and avoid injury to the operator's hand. The length of the handle is 300 mm, the pipe diameter is 32 mm, and the installation height is 800 mm from the bottom of the connector, which conforms to the ergonomic design and is convenient for workers to grip and apply force during handling and installation.

[0071] On the front of the module connector, important information such as the specification model and installation direction is clearly marked using laser marking technology. The specification model is "MJ - 2025 - A", with a character height of 15 mm and a width of 10 mm, which is clear and easy to read. The installation direction is indicated by an arrow mark filled with red paint, forming a sharp contrast with the silver metal surface of the connector, making it clearly visible even in poor lighting conditions at the construction site. In addition, the production batch, production date, and quality qualification mark are also marked next to the identification, facilitating product traceability and quality control.

[0072] During the installation process, when it is necessary to lift the module connector, use a hook that matches the size of the lifting lug, accurately place the hook into the lifting lug, ensure a secure connection, and then lift it with professional lifting equipment. After reaching the installation position, the worker adjusts the connector to the correct installation direction by grasping the handle, and according to the pre-designed installation drawing, uses high-strength bolts to connect and fix the module connector to the steel beam and steel column. After the installation is completed, check the identification content again to ensure that the installation direction is correct. At the same time, conduct a fastening inspection on the connection part of the connector to ensure the stability and reliability of the entire steel structure connection.

[0073] In some embodiments, when initially docking the module connector with the steel structure member, a positioning tooling is used to assist to ensure the docking accuracy.

[0074] In this embodiment, in the steel structure construction of a large sports stadium, a large number of H-shaped steels are used as the main structural members and are connected through module connectors. Due to the complex spatial structure of the stadium, the installation accuracy requirements for the steel structure are extremely high, and any deviation may affect the overall structural stability and subsequent stadium facility installation. To ensure the docking accuracy between the module connector and the H-shaped steel member, a positioning tooling is used to assist in the installation.

[0075] The main body of the positioning tooling is processed from 45# steel and has good strength and wear resistance. The tooling consists of a positioning frame and a positioning pin. The positioning frame is customized according to the cross-sectional dimensions of the H-shaped steel (flange width 300 mm, web thickness 12 mm, height 400 mm), and is in a U-shaped structure with internal dimensions precisely matching the H-shaped steel, with the error controlled within ±0.5 mm. Adjustable positioning bolts are provided on both sides of the positioning frame to fine-tune the position of the module connector. The positioning pin has a diameter of 20 mm and a length of 100 mm, and is quenched to improve hardness. It is installed at the corresponding hole positions of the positioning frame and the module connector to play a preliminary positioning role.

[0076] The docking process is as follows: 1. Preparation work: At the construction site, place and fix the H-shaped steel member at the designed position, and clean the impurities on the surface of the connection part. At the same time, assemble the module connector and the positioning tooling, and check whether the positioning pin can be smoothly inserted into the connector hole.

[0077] 2. Preliminary docking: Use a crane to lift the module connector with the positioning tooling above the H-shaped steel connection position and slowly lower it. When the positioning pin approaches the preset positioning hole on the H-shaped steel, manually assist in fine-tuning to accurately insert the positioning pin into the hole, initially determining the position of the module connector. At this time, the position deviation between the module connector and the H-shaped steel can be controlled within 5 mm.

[0078] 3. Precise adjustment: Fine-tune the module connector in the horizontal and vertical directions by rotating the positioning bolts on the positioning frame. Use a high-precision total station for real-time monitoring to ensure that the docking error between the module connector and the H-shaped steel does not exceed ±2 mm in the horizontal direction and ±3 mm in the vertical direction, meeting the requirements of design and construction specifications.

[0079] 4. Fixed connection: After the docking accuracy meets the standard, temporarily fix the module connector to the H-shaped steel with high-strength bolts, remove the positioning tooling for use in the docking construction of the next node. Subsequently, perform permanent welding connection, and continuously monitor during the welding process to ensure that the welding deformation does not affect the overall docking accuracy.

[0080] By using the positioning tooling to assist in docking, the installation efficiency and quality of the steel structure of the stadium have been greatly improved, reducing rework caused by docking errors, completing the construction tasks on time, and after subsequent structural inspections, all indicators meet the design requirements.

[0081] In some embodiments, the method is applicable to the node connections of steel structure factories of different types such as single-story, multi-story, and large-span.

[0082] With the technical solution of the present application, the modular combination design enables the node connection components to be prefabricated. On-site, only selection, docking, and locking are required, greatly reducing on-site processing links. With the cooperation of a quick-locking device, the construction time is significantly shortened, the construction progress of the factory building is accelerated, and the connection quality is guaranteed.

[0083] The module connectors are produced in a standardized manner with stable quality. Through the positioning tooling and professional inspection and reinforcement means, the connection accuracy and reliability are ensured. Compared with traditional on-site processing connections, problems such as welding defects and bolt loosening can be effectively avoided, the overall structural safety of the factory building is improved, and the construction difficulty is reduced.

[0084] Construction workers do not need complex on-site processing skills and only need to operate according to the process to complete the node connection, reducing the requirements for the technical level of workers. At the same time, the on-site construction equipment requirements are reduced, facilitating management and construction organization, and enhancing adaptability.

[0085] Standardized modular connectors in various specifications can flexibly meet the node connection requirements of steel structure factories of different types and specifications. Whether it is a single-story, multi-story or large-span factory building, it can quickly match the applicable connection solutions, improve the versatility and flexibility of construction, and save costs.

[0086] The improvement of construction efficiency reduces labor costs and equipment rental costs, and high-quality connections avoid additional costs caused by rework due to quality problems, reducing the total construction cost of steel structure factories in many aspects.

[0087] After considering the specification and practicing the present disclosure, those skilled in the art will readily conceive of other embodiments of the present disclosure. This application is intended to cover any variations, uses, or adaptations of the present disclosure that follow the general principles of the present disclosure and include known common knowledge or conventional technical means in the technical field not disclosed in the present disclosure. The specification and examples are only illustrative, and the true scope and spirit of the present disclosure are pointed out by the following claims.

[0088] It should be understood that the present disclosure is not limited to the exact structures described above and shown in the drawings, and various modifications and changes can be made without departing from its scope. The scope of the present disclosure is only limited by the appended claims.

Claims

1. A method for connecting joints of a steel structure factory building based on artificial intelligence, characterized in that, Including: Pre-fabricate a variety of standardized modular connectors according to the design specifications of steel structure workshops; At the construction site, for joints with different positions and specification requirements, use artificial intelligence technology to select suitable modular connectors; Conduct a preliminary docking of the modular connectors and steel structure components to align the connection interfaces with each other; Through a quick locking device, lock the docked modular connectors and steel structure components to complete the joint connection; Inspect and reinforce the connection joints to improve the stability and reliability of the connection.

2. The method for connecting joints of a steel structure workshop based on artificial intelligence according to claim 1, characterized in that The modular connectors are made of high-strength alloy steel, formed by precision casting or machining, and the surface is treated against rust.

3. The method for connecting joints of a steel structure workshop based on artificial intelligence according to claim 2, characterized in that In the step of using artificial intelligence technology to select suitable modular connectors, use digital design software with an artificial intelligence model to conduct node simulation analysis to quickly determine the type and quantity of the required modular connectors.

4. The method for connecting joints of a steel structure workshop based on artificial intelligence according to claim 3, characterized in that In the step of using artificial intelligence technology to select suitable modular connectors, using digital design software with a machine learning algorithm model to conduct node simulation analysis to quickly determine the type and quantity of the required modular connectors includes: Steps of data preparation and feature engineering, including: Collect data, including: the force condition of the joint, geometric dimensions, material properties, problem type, and the type and quantity of successfully matched connectors; Feature extraction and processing: Clean the original data, and process missing values and outliers; Numericalize the features, including: normalizing or standardizing continuous features of geometric dimensions and force conditions; Steps of model training, specifically including: Select a machine learning algorithm model; Divide the data set, and divide the prepared data into a training set, a validation set, and a test set; Use the training set to train the machine learning algorithm model. During the training process, monitor the performance of the machine learning algorithm model through the validation set to prevent overfitting; When the performance of the machine learning algorithm model on the validation set reaches the optimum, stop training; Steps of model evaluation, specifically including: Use the test set to evaluate the trained machine learning algorithm model, and calculate the accuracy rate and mean square error; For the prediction of the connector type, the accuracy rate is an index to measure the correctness of the model prediction; for the prediction of the connector quantity, the mean square error can measure the deviation degree between the predicted value and the true value.

5. The method for connecting joints of a steel structure workshop based on artificial intelligence according to claim 1, characterized in that The connection interfaces include bolt holes, card slots or tenons, and the modular connectors and steel structure components are connected by bolts, snap connections or tenon and mortise methods.

6. The method for connecting joints of a steel structure workshop based on artificial intelligence according to claim 1, characterized in that The quick locking device is a hydraulic quick clamp, a pneumatic lock or a mechanical quick locking mechanism.

7. The method for connecting nodes of a steel structure factory building based on artificial intelligence according to claim 1, characterized in that in the step of inspecting and strengthening the connection nodes, an ultrasonic flaw detector and a torque wrench tool are used to inspect the quality of the connection part, and the weak links are strengthened by welding and adding auxiliary supports.

8. The method for connecting nodes of a steel structure factory building based on artificial intelligence according to claim 7, characterized in that lifting lugs or handles for easy handling and installation are provided on the module connectors, and the specification models and installation direction marks are marked on the surface.

9. The method for connecting nodes of a steel structure factory building based on artificial intelligence according to claim 8, characterized in that when initially docking the module connectors with the steel structure components, a positioning tooling is used to assist and improve the docking accuracy.

Images