Search results

The purpose of this paper was to use visual and arc sensors to simultaneously obtain the underwater wet welding information, and a weld seam-forming model was made to predict the weld seam's geometric parameters. It is difficult to obtain a fine welding quality in underwater welding because of the intense disturbances of the water environment. To automatically control the welding quality, the weld seam-forming model should first be established. Thus, the foundation was laid for automatically controlling the underwater welding seam-forming quality.

Visual and arc sensors were used simultaneously to obtain the weld seam image, current and voltage information; then signal algorithms were used to process the information, and the back propagation (BP) neural network was used to model the process.

Experiment results showed that the BP neural network model could precisely predict the weld seam-forming parameters of underwater wet welding.

A weld seam-forming model of underwater wet welding process was made; this laid the foundation for establishing a controller for controlling the underwater wet welding process automatically.

The purpose of this study is to reduce the cracks, pores and unfused defects in arc welding, improve the crystalline structure of the weld, refine its grains and improve the mechanical properties.

Taking E690 marine steel as the research object, the experiment adopts a new process method of laser forging coupled arc welding. Welding for comparative experiments. Experiments show that the “V”-shaped groove arc welding process has a larger fusion area, but has pores, the arc current is 168 A, the arc voltage is 28 V and the welding speed is 600 mm/min.

It can be seen from tensile tests that the coupling welding process has the highest tensile strength and yield strength, 872 MPa and 692 MPa, respectively, and the fracture elongation is 29.29%. The single-beam laser forging coupled arc welding process has a distance of laser and wire of 6–8 mm, a laser wavelength of 1,064 nm and the highest weld fusion ratio. The microhardness test shows that the average hardness of single-beam laser forging in the weld zone is 487.54 HV, which is 10.30% higher than that of arc welding. The average hardness in the fusion zone is 788.08 HV, which is 14.52% higher than that of the arc welding process.

The originality of the experiment: proposed a new process method of coupling arc repair for offshore steel forging; adopted a new process method of simultaneous coupling of single-beam short-pulse laser, double-beam short-pulse laser and arc welding; and obtained effect of pulsed laser and arc composite repair on porosity and fusion of E690 marine steel welds.

Robotic friction stir welding (RFSW) is an innovative process which enables solid-state welding of aluminum parts using robots. A major drawback of this process is that the robot joints undergo elastic deformation during the welding, because of the high forces induced by the process. This leads to tool deviation and incorrect orientation. There is currently no computer-aided manufacturing/computer-aided design (CAD) software for generating off-line paths which integrates robot deflections, and the main purpose of this study is to propose an off-line methodology to plan a path for RFSW with the integration of the deflections.

The approach is divided into two steps. The first step consists of extracting position and orientation data from CAD models of the workpieces and adding the deflections calculated with a deflection model to generate a suitable path for performing RFSW. The second step consists of the smooth fitting of the suitable path using Bézier curves.

The method is experimentally validated by welding a curved workpiece using a Kuka KR500-2MT robot. A suitable tool position and orientation were calculated to perform this welding, an experimental procedure was set up, a defect-free weld was performed and a high accuracy was achieved in terms of position and orientation.

This method can help manufacturers to easily perform RFSW for three-dimensional workpieces regardless of the lateral tool deviation, loss of the right orientation and control force stability.

The originality of this method lies in compensating for robot deflections without using expensive sensors, which is the most commonly used method for compensating for robot deflection. This off-line method can lead to a reduction in programming time in comparison with teach programming method and leads to reduced investment costs in comparison with commercial off-line programming packages.

Surface forming control of welding bead is the fundamental study in automated welding. Considering that the vision sensing system cannot extract the height information of weld pool in pulsed GTAW process, so this paper designed a set of automatic measurement and control technology to achieve real-time arc height control via audio sensing system. The paper aims to discuss these issues.

The experiment system is based on GTAW welding with acoustic sensor and signal conditioner. A combination denoising method was used to reduce the environmental noise and pulse interference noise. After extracting features of acoustic signal, the relationship between arc height and arc sound pressure was established by linear fitting. Then in order to improve the prediction accuracy of that model, the piecewise linear fitting method was proposed. Finally, arc height linear model of arc sound signal and arc height is divided into two parts and built in two different arc height conditions, which are arc height 3-4 and 4-5-6 mm.

The combination denoising method was proved to have great effect on reducing the environmental noise and pulse interference noise. The experimental results showed that the prediction accuracy of linear model was not stable in different arc height changing state, like 3-4 and 4-5-6 mm. The maximum error was 0.635588 mm. And the average error of linear model was about 0.580487 mm, and the arc sound signal was accurately enough to meet the requirement for real-time control of arc height in pulse GTAW.

This paper tries to make a foundation work to achieve controlling of depth of welding pool through arc sound signal, then the welding quality control. So a new idea of arc height control based on automatic measuring and processing system through arc sound signal was proposed. A new way to remove environmental noise and pulse interference noise was proposed. The results of this thesis had proved that arc sound signal was an effective features and precisely enough for online arc height monitoring during pulsed GTAW.

The purpose of this study is to develop a robotic training system for the hand movements during manual welding. The system provides real-time notice-feedback with sound or light alarms, whenever the welding hand vibrates beyond the nominal level observed with professional welders.

The large variations of hand movements are detected by monitoring the deviation of the tool position from a smooth curve estimated in real time by a Kalman filter. An alarm is generated in the form of a flashing light or beep sound whenever the deviations exceed a predetermined threshold. The performance of hand movements is measured in terms of the variations of the position data. Twelve novice and five professional welders took part in the experiments and answered a questionnaire that assessed the usability and work load of the system.

Compared to the sound alarms, the light alarms resulted in a larger and statistically significant decrease in the variation of hand movements of the novice welders and brought the level of variation close to that of the professional welders. The alarms did not result in a significant decrease in the variation of hand movements of the professional welders. The responses to the questionnaire indicated that both professional and novice welders found the system useful and they did not experience any significant work load.

The system developed in this study can ease the training of novice welders, by speeding up the learning and reducing the need for human tutors.

This study is first to provide real-time notice-feedback for training while manual welding, based on a comparison of the performances of novice and professional welders.

Penetration state is one of the most important factors for judging the quality of a gas tungsten arc welding (GTAW) joint. The purpose of this paper is to identify and classify the penetration state and welding quality through the features of arc sound signal during robotic GTAW process.

This paper tried to make a foundation work to achieve on‐line monitoring of penetration state to weld pool through arc sound signal. The statistic features of arc sound under different penetration states like partial penetration, full penetration and excessive penetration were extracted and analysed, and wavelet packet analysis was used to extract frequency energy at different frequency bands. The prediction models were established by artificial neural networks based on different features combination.

The experiment results demonstrated that each feature in time and frequency domain could react the penetration behaviour, arc sound in different frequency band had different performance at different penetration states and the prediction model established by 23 features in time domain and frequency domain got the best prediction effect to recognize different penetration states and welding quality through arc sound signal.

This paper tried to make a foundation work to achieve identifying penetration state and welding quality through the features of arc sound signal during robotic GTAW process. A total of 23 features in time domain and frequency domain were extracted at different penetration states. And energy at different frequency bands was proved to be an effective factor for identifying different penetration states. Finally, a prediction model built by 23 features was proved to have the best prediction effect of welding quality.

The purpose of this paper is to develop an efficient online monitoring system. It can improve the welding quality through the real‐time analysis of the welding image information.

In this paper, a set‐variable precision rough set (VPRS) modeling method was improved and the prediction model of back‐side bead width dynamic response for robotic arc welding process is proposed. Back‐side width based on the vision sensor in the compound controller is used. Meantime, a compound intelligent controller is designed with the wire‐feeding rate compensation.

The dynamical information of the top‐side weld pool can be captured in real‐time. Moreover, VPRS prediction model could provide the back‐side bead width of the weld, which integrated with the fuzzy neural network controller. Therefore, more uniform weld penetration can be achieved with the variation of the assembling gap.

The monitor system requires that the information of the weld pool and the front gap can be extracted precisely. Moreover, the front assembling gap should be limited in a certain interval [0∼3 mm]. This puts forward high request to image processing algorithm and the assembling of the work‐piece.

This monitor system is applicable to the manufacturing of the spherical head petals in rocket storage tank.

The paper demonstrates that the compound intelligent controller based on the VPRS prediction is possible and effective. The experiments show that the real‐time and precision requirements for monitoring and control of weld quality can be satisfied by using this online control system during welding process.

The purpose of this paper is to develop a kind of low cost measuring system based on binocular vision sensor to detect both the weld pool geometry and root gap simultaneously for robot welding process.

Two normal charge coupled device cameras are used for capturing clear images from two directions; one of them is used to measure the root gap and another one is used to measure the geometric parameters of the weld pool. Efforts are made from both hardware and software aspects to decrease the strong interferences in pulsed gas tungsten arc welding process, so that clear and steady images can be obtained. The grey level distribution characteristics of root gap edge and weld pool edge in images are analyzed and utilized for developing the image processing algorithms.

A solid foundation for seam tracking and penetration control of robot welding process can be established based on the binocular vision sensor.

The results show that the algorithms can extract the root gap edges and the contour of weld pool effectively, and then some geometric parameters can be calculated from the results.

The binocular vision system provides a new method for sensing of robot welding process.

Investigates the potential for building smart seams by incorporating optic fibers ultrasonically. The heating and bonding mechanisms of ultrasonic welding process in fabrics were studied. Battle dress uniform (BDU) (50/50 nylon/cotton), 100 percent cotton, 100 percent polyester and Nomex fabrics were used and were bonded ultrasonically with and without polyurethane adhesives. The effects of three important welding parameters, namely weld pressure, weld time and amplitude of vibration, on the joint strength and the temperature profile at the interface were examined. The temperature profiles for different fabrics were measured during ultrasonic welding process. The attenuation degree of signal transition properties of optic fibers incorporated was tested to determine if ultrasonic process provided a possible way of embedding optic fibers into seams and achieving sufficient joint strength while the signal transmission properties of optic fibers incorporated were not changed significantly.

The purpose of this paper is to introduce structured light image processing technology into pipeline welding automation projects, and develop a vision‐based pipeline girth‐welding robot. The welding torch can accurately track the weld and complete the omni‐orientation welding automatically.

Weld image processing adopts the base theory including Laplacian of Gaussian filter, neighbourhood mean filter, largest variance threshold segmentation and morphologic, etc. obtains good effect of weld recognition.

The paper uses a vision sensor to achieve the weld character's recognition and extraction, directly control the robot tracking weld to complete automation welding. Compared with the existing pipeline welding devices, it does not need the lay orbit or plot tracking mark, which can shorten the assistant time to improve the productivity.

The research findings can satisfy the need of whole‐directional automation welding for large diameter transportation pipe's circular abutting weld. It fits for the automation welding for the long‐distance transportation pipe of petroleum, natural gas, and water.

Aiming at the character recognition and extract of V‐type weld, the method combining the neighbourhood mean filter algorithm with the largest variance threshold segmentation is proposed to obtain the quick weld image processing speed.