Search results

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.

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 paper is to study the relationship between arc sound signal and arc height through arc sound features of GTAW welding, which is aimed at laying foundation work for monitoring the welding penetration and quality by using the arc sound signal in the future.

The experiment system is based on GTAW welding with acoustic sensor and signal conditioner on it. The arc sound signal was first processed by wavelet analysis and wavelet packet analysis designed in this research. Then the features of arc sound signal were extracted in time domain, frequency domain, for example, short‐term energy, AMDF, mean strength, log energy, dynamic variation intensity, short‐term zero rate and the frequency features of DCT coefficient, also the wavelet packet coefficient. Finally, a ANN (artificial neural networks) prediction model was built up to recognize different arc height through arc sound signal.

The statistic features and DCT coefficient can be absolutely used in arc sound signal processing; and these features of arc sound signal can accurately react the modification of arc height during the GTAW welding process.

This paper tries to make a foundation work to achieve monitoring arc length through arc sound signal. A new way to remove high frequency noise of arc sound signal is produced. It proposes some effective statistic features and a new way of frequency analysis to build the prediction model.

The purpose of this paper is to analyze the characteristics of sound during gas tungsten argon welding (GTAW), which is very important to effectively monitor the welding quality in future by using the information extracted from sound.

The hardware used in the experiment is described. Then the paper researches the influence of welding techniques (gas flow, welding speed, welding current, and arc length) on arc sound and the distribution of the welding sound field. Finally, the relation between welding power and sound are studied based on Fourier transforms and recursive least square methods.

The sound pressure is affected greatly by gas flow, arc length, and current; welding sound source obeys the dipole model; the sound can be better predicted when the three orders derivative of the welding power are combined together.

This paper provides a new insight into welding sound resource model and a detailed analysis of the influence of the welding sound caused by welding techniques.

The purpose of this paper was to propose a method based on an Artificial Neural Network and a real-time vision algorithm, to learn welding skills in industrial robotics.

By using an optic camera to measure the bead geometry (width and height), the authors propose a real-time computer vision algorithm to extract training patterns and to enable an industrial robot to acquire and learn autonomously the welding skill. To test the approach, an industrial KUKA robot and a welding gas metal arc welding machine were used in a manufacturing cell.

Several data analyses are described, showing empirically that industrial robots can acquire the skill even if the specific welding parameters are unknown.

The approach considers only stringer beads. Weave bead and bead penetration are not considered.

With the proposed approach, it is possible to learn specific welding parameters despite of the material, type of robot or welding machine. This is due to the fact that the feedback system produces automatic measurements that are labelled prior to the learning process.

The main contribution is that the complex learning process is reduced into an input-process-output system, where the process part is learnt automatically without human supervision, by registering the patterns with an automatically calibrated vision system.

The performance of a welding process determines not only the cost, but also the quality of the product. How to control the welding process in order to ensure good welding performance with less cost and higher Productivity has become critical. The objective of this study is twofold: (1) developing artificial neural networks to predict welding performance using different learning algorithms: back propagation, simulated annealing and tabu search; (2) comparing and discussing the performance of neural networks trained using those algorithms. Statistical analysis shows that back propagation is able to make more accurate prediction than the other algorithms for this particular application. However, all three algorithms demonstrate impressive flexibility and robustness.

Welding sensor technology is the key technology in welding process, but a single sensor cannot acquire adequate information to describe welding status. This paper addresses arc sensor and sound sensor to acquire the voltage and sound information of pulsed gas tungsten arc welding (GTAW) simultaneously, and uses multi‐sensor information fusion technology to fuse the information acquired by the two sensors. The purpose of this paper is to explore the feasibility and effectiveness of multi‐sensor information fusion in pulsed GTAW.

The weld voltage and weld sound information are first acquired by arc sensor and sound sensor, then the features of the two signals are extracted, and the features are fused by weighted mean method to predict the changes of arc length. The weights of each feature are determined by optional distribution method.

The research findings show that multi‐sensor information fusion technology can effectively utilize the information of different sensors and get better result than single sensor.

The arc sensor and sound sensor are first used at the same time to get information about pulsed GTAW and the fusion result shows its advantages over single sensor; this reveals that multi‐sensor fusion technology is a valuable research area in welding process.

The status of welding process is difficult to monitor because of the intense disturbance during the process. The purpose of this paper is to use multiple sensors to obtain information about the process from different aspects and use multi‐sensor information fusion technology to fuse the information, to obtain more precise information about the process than using a single sensor alone.

Arc sensor, visual sensor, and sound sensor were used simultaneously to obtain weld current, weld voltage, weld pool's image, and weld sound about the pulsed gas tungsten‐arc welding (GTAW) process. Then special algorithms were used to extract the signal features of different information. Fuzzy measure and fuzzy integral method were used to fuse the extracted signal features to predict the penetration status about the welding process.

Experiment results show that fuzzy measure and fuzzy integral method can effectively utilize the information obtained by different sensors and obtain better prediction results than a single sensor.

Arc sensor, visual sensor, and sound sensor are used in pulsed GTAW at the same time to obtain information, and fuzzy measure and fuzzy integral method are used to fuse the different features in welding process for the first time; experiment results show that multi‐sensor information can obtain better results than single sensor, this provides a new method for monitoring welding status and to control the welding process more precisely.

The purpose of this paper is to investigate the relationship between the keyhole geometry and acoustic signatures from the backside of a workpiece. It lays a solid foundation for monitoring the penetration state in variable polarity keyhole plasma arc welding.

The experiment system is conducted on 6-mm-thick aluminum alloy plates based on a dual-sensor system including a sound sensor and a charge coupled device (CCD) camera. The first step is to extract the keyhole boundary from the acquired keyhole images based on median filtering and edge extraction. The second step is to process the acquired acoustic signal to obtain some typical time domain features. Finally, a prediction model based on the extreme learning machine (ELM) technique is built to recognize different keyhole geometries through the acoustic signatures and then identify the welding penetration status according to the recognition results.

The keyhole geometry and acoustic features after processing can be closely related to dynamic change information of keyhole. These acoustic features can predict the keyhole geometry accurately based on the ELM model. Meanwhile, the predict results also can identify different welding penetration status.

This paper tries to make a foundation work to achieve the monitoring of keyhole condition and penetration status through image and acoustic signals. A useful model, ELM, is built based on these features for predicting the keyhole geometry. Compared with back-propagating neural network and support vector machine, this proposed model is faster and has better generalization performance in the case studied in this paper.

Development of non‐destructive methodology for detection of arc strike, spatter and fusion type of welding defects which may form on steam generator (SG) tubes that are in close proximity to the circumferential shell welds. Such defects, especially fusion‐type defects, are detrimental to the structural integrity of the SG. This paper aims to focus on this problem.

This paper presents a new methodology for non‐destructive detection of arc strike, spatter and fusion type of welding defects. This methodology uses remote field eddy current (RFEC) ultrasonic non‐destructive techniques and K‐means clustering.

Distinctly different RFEC signals have been observed for the three types of defects and this information has been effectively utilized for automated identification of weld fusion which produces two back‐wall echoes in ultrasonic A‐scan signals. The methodology can readily distinguish fusion‐type defect from arc strike and spatter type of defects.

The methodology is unique as there is no standard guideline for non‐destructive evaluation of peripheral tubes after shell welding to detect arc strike, spatter and fusion type of welding defects.