最新刊期
期 9 ， 2023
- 摘要：Laser additive manufacturing (LAM) uses the laser as the energy beam to melt and deposit metal layer by layer to form components, considering both manufacturing efficiency and forming accuracy. It has received widespread attention in the fields of national defense engineering and aerospace. Improving the stability of the manufacturing process, optimizing forming accuracy, and eliminating internal defects are key scientific and technological challenges that must be addressed to promote the efficient and high-quality development and application of LAM. Implementing online monitoring and control in LAM is necessary to address these challenges. The generation mechanism and corresponding suppression measures of LAM forming defects are analyzed, the monitoring methods and research status of LAM process signals are elaborated, and the closed-loop control strategies of LAM quality are discussed. The main research directions of process monitoring and control for LAM in the future are advised.关键词：laser additive manufacturing;online monitoring;process control;forming quality;defect
- 30
- |
- 12
- |
- 0
发布时间：2023-09-28 - 摘要：In the application of automatic welding, offline programming welding robots usually has certain control limitations. This paper combines virtual reality technology to build a welding robot workstation. By developing an offline programming system to simplify robot control methods, flexibly adjust perspectives, and automatically plan welding trajectories for improving offline programming efficiency. Proposed the same point and different lines weld seam recognition algorithm and implemented trajectory planning function for single robot. Based on welding torch reference posture, by analyzing the welding posture of horizontal welding, flat welding, vertical upward welding, and vertical downward welding to realize all position welding posture planning. Built the welding robot workstation by adding a KBR-2Z500 dual-axis positioner, and realized multi-axis linkage complex trajectory planning function. Coupling and decoupling between robot motion and positioner motion discussed to solve the problem of welding robot workstation cooperative motion planning. In real space, replicated virtual environment spatial curve welding trajectory planning experiments. The interactivity, feasibility and reliability of the developed offline programming system has been verified.关键词：virtual reality;offline programming;welding robot;weld recognition;two-machine coordination
- 22
- |
- 9
- |
- 0
发布时间：2023-09-28 - 摘要：With the continuous adjustment of our country's energy structure, the large-scale, refined, and scaled LNG storage tanks have become the mainstream trend driving the development of our liquefied natural gas industry. The welding quality, welding efficiency, and level of intelligence in the process of welding the inner tank vertical seam and filling cover directly affect the reliability of the welded joints, the flexibility of structural design, and the construction cost of LNG storage tanks. Currently developed semi-automatic welding machines for LNG storage tanks have a low level of intelligence in the process of welding the inner tank vertical seam, excessively relying on manual labor, and facing challenges in harsh welding environments. This article analyzes the existing problems of the current semi-automatic welding machines and proposes corresponding improvement plans. By incorporating bottom welding fusion penetration control and adaptive intelligent sensing systems for filling cover, it further enhances the level of intelligence and welding efficiency, providing some insights for the intelligent welding development of inner tank vertical seams in LNG storage tanks.关键词：LNG storage tank;vertical seam;TIP TIG Welding;intelligent welding;fusion penetration control;intelligent sensing systems
- 26
- |
- 20
- |
- 0
发布时间：2023-09-28 - 摘要：In order to improve the programming efficiency of welding robot and ensure the welding quality, the development of robot kinematics simulation and control system was studied. First of all, the D-H parameter method is used to model and solve the forward and inverse kinematics of the welding robot. Then, the automatic path planning of the intersection line is studied by constructing the coordinate system of welding seam, and the PC SDK is used to communicate with the robot controller. Based on VisualStudio C# platform and OpenGL, the robot kinematics simulation, automatic path planning and remote arc welding control of functions are realized. Finally, the basic functions of the system were verified through RobotStudio, and the results showed that the system was accurate and reliable, and met the working requirements of welding robot, greatly improving work efficiency, and providing a solution for the development of robot simulation and remote control systems.关键词：industrial robot;robot simulation;welding system;robot kinematics;path planning
- 57
- |
- 16
- |
- 0
发布时间：2023-09-28 - 摘要：Austenitic stainless steel pipelines are widely utilized in high-performance service equipment due to their advantageous properties, including excellent corrosion resistance, high-temperature strength, easy work hardening, and non-magnetic characteristics in the solid solution state. However, the high thermal expansion coefficient of austenitic stainless steel can result in weld deformation during the welding process, while its low thermal conductivity can lead to poor fluidity in the molten pool, increasing the likelihood of welding defects such as pores and inclusions. This study focuses on narrow gap laser all-position welding of austenitic stainless steel pipes. The Fluent simulation software is utilized to numerically simulate the laser welding process. Additionally, the temperature field distribution and weld shape characteristics of welded joints under different laser power and welding speed conditions are investigated. Experimental research on narrow gap laser welding is carried out at various spatial positions during robot welding. The impact of welding parameters, including laser power, welding speed, and defocus, on weld formation is determined, thus providing fundamental data for all-position robot welding of stainless steel pipelines.关键词：stainless steel pipeline;welding robot;narrow gap laser welding;weld formation
- 15
- |
- 54
- |
- 0
发布时间：2023-09-28 - 摘要：Weld penetration recognition and control is of great significance to improve welding quality and automation level of Fast-frequency Pulsed Tungsten Inert Gas welding (FFP-TIG welding). Weld pool images can be used as the input of convolutional neural network (CNN) to recognize the penetration state, but the model is often complex and difficult to deploy in industrial edge devices. At the same time, it lacks control methods for penetration state based on recognition results. To solve this problem, a visual sensing system was established to construct the FFP-TIG welding pool image dataset of 304 stainless steel, including lack of penetration, desirable penetration, and excessive penetration. A penetration recognition model based on knowledge distillation (KD) was developed, which utilized MobileNetV2 as the teacher model for training ResNet-KD that is a custom student model. Based on the softmax layer output of ResNet-KD, a fuzzy controller was designed to adjust the fast-frequency base current in real-time and realize closed-loop control of the penetration state. The results showed that the recognition accuracy of ResNet-KD on the validation set achieved 97.60%, and the fuzzy controller had good performance under the conditions of presetting initial cparameters, heat dissipation variation and heat accumulation.关键词：FFP-TIG welding;weld pool image;penetration recognition;knowledge distillation;fuzzy control
- 14
- |
- 10
- |
- 0
发布时间：2023-09-28 - 摘要：Laser vision sensing technology has become one of the mainstream welding seam tracking techniques due to its features of non-contact, high precision, and fast response. However, in the actual welding process, strong interferences such as arc light and spatter can lead to drift of laser vision feature points and failure in information extraction. To mitigate the interference caused by strong arc light and spatter during the high-current CO2 gas shielded welding, an offline visual measurement method is employed to inspect the workpiece to be welded. The acquired images are processed through composition morphological filtering and Euclidean distance transform. Using the differential method, the groove position information is extracted. Subsequently, grouping averaging and interpolation methods are employed to obtain complete welding trajectory data, which is then transmitted to the lower-level controller for automated welding. Ultimately, a uniformly formed weld seam free from defects such as porosity and underfill is achieved.关键词：laser vision;weld seam tracking;image processing;weld seam trajectories;offline planning
- 10
- |
- 19
- |
- 0
发布时间：2023-09-28 - 摘要：The application of welding robots effectively improves labor productivity, reduces worker labor intensity, and has good stability. Visual sensing technology can empower welding automation technology, which can help welding workstations more accurately complete welding tasks by detecting the shape, size, position, and welding quality of welds. This article explains the construction of intelligent welding robot workstations, the way visual sensing is deployed, and the working principles of various visual sensing technologies in welding seam positioning, tracking, and quality inspection. The current mainstream techniques, including line structured light method, point structured light scanning method, multi-line structured light method, and surface structured light method, are described and summarized in detail, each with different characteristics that require matching with specific application scenarios. Welding visual technology can help enterprises better control welding quality, improve production efficiency, reduce production costs, and provide more possibilities for the development of the welding industry.关键词：welding robot;visual sensing;structured light;three-dimensional vision
- 13
- |
- 12
- |
- 0
发布时间：2023-09-28 - 摘要：With the wide application of welding technology in industrial environment, more and more scholars pay attention to the study of welding defects. As one of the most serious defects in the welding process, the corresponding measures must be taken to monitor and control the burn-through defects. In this paper, a passive visual sensing technique is proposed to eliminate the strong arc light interference in the welding process by using industrial CCD camera combined with dimming and filtering system, then obtain MIG welding pool image. Based on the multi-dimensional features of the image, ten dimensional features corresponding to the four categories of molten pool image are extracted as the input of machine learning. During the label calibration of normal and burn-through defects, the image data of molten pool obtained from orthogonal test were preprocessed based on the proposed feature extraction, the invalid data were eliminated and the valid data were correctly classified by reverse search. Meanwhile, the spatial distribution of data was found. Finally, the recognition effects of the three classifiers under the input features of different dimensions were explored, and the results showed that the selected features obtained classification accuracy of no less than 97% on the three classifiers, which provided technical support and theoretical basis for the subsequent development of visual online burn-through defects detection system.关键词：MIG welding;vision sensing;molten pool image processing;machine learning;defect identification
- 7
- |
- 9
- |
- 0
发布时间：2023-09-28 - 摘要：In order to address the automation requirements of multi-layer and multi-pass welding for medium-thick plates, this paper proposes a robot welding path adaptive planning algorithm based on point cloud data. Taking V-groove welds as an example, the weld surface is scanned using a line structured light system to collect point cloud data. Then the point cloud data is preprocessed through the filtering method to reduce the data size and remove noise points, and the resultant welding feature points are successfully extracted by the point cloud segmentation and edge extraction algorithms. Finally, welding experiments are carried out to verify the accuracy and feasibility of the proposed algorithm. The results show that the average deviation between the coordinates of weld feature points obtained by the proposed algorithm and the actual coordinates obtained by manual teaching is less than 0.17 mm, which meets the practical application requirements.关键词：Robot welding;point cloud data-driven;multi-layer multi-pass welding;path planning;line structured light
- 7
- |
- 15
- |
- 0
发布时间：2023-09-28 - 摘要：Pulsed laser welding of aluminum alloy is widely used in precision machining fields such as power batteries and new energy vehicles because it can accurately adjust the laser energy input. However, the inherent properties of aluminum alloy such as high thermal conductivity and high reflectivity, as well as the intense interaction with high energy laser, bring challenges to the optimization of process parameters and welding quality assurance. In this paper, the influences of different pulse laser parameters (peak power, pulse frequency and welding speed) on weld forming were analyzed. Taking the process parameters as multi-dimensional input features, the prediction model of melting width and depth based on BP neural network was further constructed. The results show that different process parameters have direct influences on the weld depth and width, and it is necessary to determine a suitable process window. At the same time, the average prediction error of the constructed model is less than 10%, which has a high prediction accuracy. The research provides a reliable experimental and guiding basis for the quality prediction and process optimization of pulsed laser welding of aluminum alloy.关键词：Pulsed Laser Welding;1060 aluminum alloy;Weld size;neural network;quality prediction
- 5
- |
- 22
- |
- 0
发布时间：2023-09-28 - 摘要：Some surfaces of cylinder head of marine diesel engine are under high temperature and high pressure for a long time when it is in operation, and the parent material is very easy to be damaged. Therefore, a layer of nickel base alloy material will be welded on the surface to improve its high temperature and high pressure resistance in actual production. At present, manual electrode arc welding and special machine semi-automatic welding are mainly used in factory, but there are some problems like low efficiency, poor flexibility and large amount of manual participation. In view of this phenomenon, a marine diesel engine cylinder head welding system based on laser searching is developed. Robots are used to replace manual work, laser sensors are used to searching the welding position, and then the welding procedure is offset to the correct position without manual intervention during the period. A single cylinder head only needs to be positioned once, which saves a lot of time for manually positioning the weld seam and improves the production efficiency. It can shorten the production cycle and improve the efficiency by more than 20% compared with the special machine semi-automatic welding.This system has strong practical significance.关键词：laser searching;cylinder head;welding;robot;intelligent;automatic
- 5
- |
- 9
- |
- 0
发布时间：2023-09-28 - 摘要：Welding is an indispensable processing method in modern manufacturing. With the development of modern manufacturing, the demand for welding automation and intelligence is increasing. And welding process quality monitoring is the premise of welding automation and intelligence. Welding process quality monitoring mainly includes two aspects: welding process information collection and analysis. This work describes welding process quality monitor technologies of the most widely used arc welding mainly from the information sensed from the welding and data analytic technologies two aspects. The former includes the instantaneous electrical information, the acoustic information, the optical information and the fusion of multi-source information; and the latter includes statistical methods and machine learning methods. And proposed the shortcomings of existing research and future research needs.关键词：arc welding;quality monitoring;data sensing;statistical analysis;machine learning
- 15
- |
- 7
- |
- 0
发布时间：2023-09-28 - 摘要：In order to clarify the action mechanism of active flux on the molten pool during laser welding of aluminum alloys, a mathematical model of the molten pool with a three-dimensional transient moving heat source was established. The influence of surface tension gradient and laser absorptivity on the temperature field and flow field was studied, so as to reveal the enhancement mechanism of penetration depth under the action of active flux. The results showed that the simulated weld morphology was consistent with the actual test results without active flux. In low-power active laser welding of aluminum alloys, although the addition of active flux changed the surface tension gradient, the change of surface tension gradient had no obvious effect on the increase of penetration depth. The analysis showed that the main reason for the increase of penetration depth was the increase of laser absorption rate with the addition of active flux.关键词：active flux;laser welding;aluminum alloys;dynamic behavior of molten pool;influence mechanism
- 8
- |
- 20
- |
- 0
发布时间：2023-09-28 - 摘要：GH3230 nickel-based superalloy was prepared by selective laser melting (SLM). The influence of process parameters on forming defects of GH3230 nickel-based superalloy was studied. The results show that when the scanning speed is 900 mm/s, the laser power is 210 W, the scanning distance is 0.09 mm, and the thickness of the powder layer is 0.04 mm, the minimum porosity of the formed sample is 0.010 8%. The results of the study on the effect of solution treatment on the microstructure and mechanical properties of the samples with the best parameters show that a large number of linear carbide particles will be deposited on the surface of the GH3230 superalloy formed after solution treatment. With the extension of holding time, the size and number of carbide particles will first increase and then decrease, and recrystallization will occur in the alloy. At the same time, the yield strength and tensile strength of molded specimens decreased from 421.8 MPa to 347.8 MPa, from 763.4 MPa to 678.9 MPa, and the elongation increased from 17.19% to 21.2%. The strength of the alloy decreases while the plasticity increases.关键词：selective laser melting (SLM);GH3230 alloy;porosity;solution treatment
- 4
- |
- 23
- |
- 0
发布时间：2023-09-28
Human-machine Cooperation & Intelligent Welding
- Postal code：610051
- Tel：028-83289008
- Technical support is provided by Beijing Founder electronics co., LTD 蜀ICP备07004068号-2
公网安备11010802024621 - It is recommended to read the content of this site in Chrome&IE9+. Please switch to extreme mode in browser 360.
- Cookies We use cookies to help provide and enhance our service and tailor content. By continuing, you agree to the use of cookies.
0