Intelligent systems for welding process automation

Alfaro, Sadek Crisóstomo Absi; Drews, Paul

doi:10.1590/s1678-58782006000100002

Cited by 9 publications

(5 citation statements)

References 8 publications

(4 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…General Real-time weld quality inspection for defect detection thanks to current, voltage, and welding speed parameters [15] Artificial Through algorithms to predict weld deposition efficiency using arc sound signal, current, and voltage [91] Artificial Development of intelligent systems for welding process automation [92] Artificial For automatic real-time defect detection and classification based on the combined use of principal component analysis [33] Deep For real-time porosity defect prediction and detection based on the voltage signal [39] Once the data has been analyzed with one of the mathematical formulations, to study and improve the modeling technique, we can rely on the various neural networks with their modular software interfaces; look at Table 1 for several examples:…”

Section: Neural Network Type Processes Referencesmentioning

confidence: 99%

“…By implementing an artificial neural network to sensor fusion, the following elements are improved [92]:…”

mentioning

confidence: 99%

“…Developing intelligent systems for the automation of the welding process for the implementation of an artificial neural network, used to improve computer vision based on photogrammetry and sensor fusion monitoring using fuzzy logic [92].…”

mentioning

confidence: 99%

See 2 more Smart Citations

Advances in Robotic Welding for Metallic Materials: Application of Inspection, Modeling, Monitoring and Automation Techniques

Curiel

Veiga

Suárez³

et al. 2023

Metals

View full text Add to dashboard Cite

The robotic welding manufacturing of metal parts is a very important process, especially in heavy industries such as shipbuilding, oil and gas, automotive, and aerospace. There is a great variety of different techniques for manufacturing by robotic welding, and the welding operations are always in a constant process of evolution, as any advance can be significant to avoid defects during the welding process. Although a great deal of research work has been carried out in recent years, thanks to which results and reviews have been presented on this subject, the main aim of this publication is to define and review works that show the advances in the main inspection, modeling, monitoring, and automated operations during the welding process to avoid, or predictively identify, any possible defect in order to obtain an optimum degree of quality in the welding.

show abstract

Section: Neural Network Type Processes Referencesmentioning

confidence: 99%

“…By implementing an artificial neural network to sensor fusion, the following elements are improved [92]:…”

mentioning

confidence: 99%

See 1 more Smart Citation

Advances in Robotic Welding for Metallic Materials: Application of Inspection, Modeling, Monitoring and Automation Techniques

Curiel

Veiga

Suárez³

et al. 2023

Metals

View full text Add to dashboard Cite

show abstract

“…In [75], a video system was coupled to the torch to observe the welding pool directly in a GMAW process, and a sensor for optical seam tracking was put in front of the torch. The sensor fusion was implemented using 12 distributed processing units and specialized nodes that implement an artificial neural network used to improve photogrammetry-based computer vision.…”

Section: Sensor Fusion In Arc Welding Processesmentioning

confidence: 99%

Measurement and estimation of the weld bead geometry in arc welding processes: the last 50 years of development

Bestard

Alfaro

2018

J Braz. Soc. Mech. Sci. Eng.

View full text Add to dashboard Cite

The arc welding process is widely used in industry, but the automatic control is limited by the difficulty in the process for measuring the principal magnitudes and to close the control loop. Adverse environmental conditions make use of conventional measurement systems difficult for obtaining information of the weld bead geometry. Under these conditions, indirect sensing techniques are a good option. Different sensing and estimation techniques are used, but few researchers are focusing on the flat welding position. The theory and practice prove that the dynamic models are the best representation to control the welding process, but most studies are performed with static models. This work is a review of the algorithms and sensing techniques used for collecting values of the arc welding process that allow the measurement or estimation of the weld bead geometry. Special attention is given to sensor fusion techniques due to its promising future in the welding process. Discussed in this text are the papers, patents, thesis and other documents found on the theme. It shows a summary of their evolution over the last 50 years.

show abstract

“…Moreover, the non-conventional parameters, at the present, are not used enough to evaluate the welding quality. They are some non-contact methods for welding monitoring process as acoustical sensing [8][9][10][11][12][13][14][15], spectroscopy emission [16][17][18], infrared emission [19][20][21] and sensoring combination [22].…”

Section: (3)mentioning

confidence: 99%

Sensors for quality control in welding

Alfaro

2012

Soldag. insp.

View full text Add to dashboard Cite

The classical inspection methods used for detecting and finding disturbances in welding process are based on direct measurement of its parameters as arc voltage, welding current, wire feed speed, etc. Using these inspection methods implies sensors insertion around the welding process and its presence could alter the metallic transference behavior and consequently an uneven quality as well as it can increase the production cost. For reducing these implications is necessary using a non intrusive inspection method. In this paper we will show nonintrusive methods to the weld quality inspection. These methods are based on sensor fusion, the extraction of global information coming from the interrelation data given by each sensor that, for example, sensing the spectroscopy radiation emission, the acoustic sensing of the electrical arc, the infrared emissions indicating the heat content of the weld. Finally, the fusion data will be applied to a statistical control for detecting and finding welding disturbances. The results will show that sensor fusion could be used as a tool to measure indirectly the weld quality in the GMAW process. Key-words: Quality Control in Welding, Spectroscopy, Acoustic sensing, Infrared emission, Sensor fusion. Resumo: Os métodos clássicos de inspeção utilizados para detectar e encontrar perturbações nos processos de soldagem são baseados comumente na medição direta de seus parâmetros como da tensão do arco, corrente de soldagem, velocidade de alimentação, etc. Usando esses métodos de inspeção implica inserção dos sensores em todo o processo de soldagem e sua presença poderia alterar o comportamento, por exemplo, da transferência metálica e, consequentemente, uma qualidade irregular da junta soldada, bem como provocaria o aumento do custo de produção. Para reduzir essas implicações é necessário usar um método de inspeção não intrusiva.

show abstract

Intelligent systems for welding process automation

Cited by 9 publications

References 8 publications

Advances in Robotic Welding for Metallic Materials: Application of Inspection, Modeling, Monitoring and Automation Techniques

Advances in Robotic Welding for Metallic Materials: Application of Inspection, Modeling, Monitoring and Automation Techniques

Measurement and estimation of the weld bead geometry in arc welding processes: the last 50 years of development

Sensors for quality control in welding

Contact Info

Product

Resources

About