A robust butt welding seam finding technique for intelligent robotic welding system using active laser vision

Multi-layer/multi-pass welding (MLMPW) technology is widely used in the energy industry to join thick components. During automatic welding using robots or other actuators, it is very important to recognize the actual weld pass position using visual methods, which can then be used not only to perform reasonable path planning for actuators, but also to correct any deviations between the welding torch and the weld pass position in real time. However, due to the small geometrical differences between adjacent weld passes, existing weld position recognition technologies such as structured light methods are not suitable for weld position detection in MLMPW. This paper proposes a novel method for weld position detection, which fuses various kinds of information in MLMPW. First, a synchronous acquisition method is developed to obtain various kinds of visual information when directional light and structured light sources are on, respectively. Then, interferences are eliminated by fusing adjacent images. Finally, the information from directional and structured light images is fused to obtain the 3D positions of the weld passes. Experiment results show that each process can be done in 30 ms and the deviation is less than 0.6 mm. The proposed method can be used for automatic path planning and seam tracking in the robotic MLMPW process as well as electron beam freeform fabrication process.

show abstract

“…filtering using color space conversion to utilize the specific color information in RGB image [ 14 ], etc.…”

Section: Figurementioning

confidence: 99%

A Weld Position Recognition Method Based on Directional and Structured Light Information Fusion in Multi-Layer/Multi-Pass Welding

Zeng

Chang

et al. 2018

Sensors

View full text Add to dashboard Cite

show abstract

“…As laser welding defects on the safety vent of a battery may cause overheating or explosion over time when it is in use, the quality control of laser welding is very critical, which helps to prolong the life of the batteries and ensure the safety of the batteries. At present, the main methods to detect the quality of welding include laser [3], ultrasonic [4], X-ray [5,6], machine vision [7,8], and so on, which have been widely used by many companies to inspect welding quality during manufacturing. Benefiting from the development of image processing algorithms and camera technology, machine vision is playing a significant role in modern industries for real-time quality assurance [7].…”

Section: Introductionmentioning

confidence: 99%

A High-Performance Deep Learning Algorithm for the Automated Optical Inspection of Laser Welding

Yang

Pan

et al. 2020

Applied Sciences

View full text Add to dashboard Cite

The battery industry has been growing fast because of strong demand from electric vehicle and power storage applications.Laser welding is a key process in battery manufacturing. To control the production quality, the industry has a great desire for defect inspection of automated laser welding. Recently, Convolutional Neural Networks (CNNs) have been applied with great success for detection, recognition, and classification. In this paper, using transfer learning theory and pre-training approach in Visual Geometry Group (VGG) model, we proposed the optimized VGG model to improve the efficiency of defect classification. Our model was applied on an industrial computer with images taken from a battery manufacturing production line and achieved a testing accuracy of 99.87%. The main contributions of this study are as follows: (1) Proved that the optimized VGG model, which was trained on a large image database, can be used for the defect classification of laser welding. (2) Demonstrated that the pre-trained VGG model has small model size, lower fault positive rate, shorter training time, and prediction time; so, it is more suitable for quality inspection in an industrial environment. Additionally, we visualized the convolutional layer and max-pooling layer to make it easy to view and optimize the model.

show abstract

“…Singapore, Switzerland and other countries related technical personnel first proposed to realize intelligent control of urban lighting based on computer technology. However, with the increasing expansion of the city and the diversified development of demand, this control strategy has been unable to meet the needs of the times [12][13]; relevant German scientific research institutions have developed intelligent street lamp control system based on bus control, which can realize the collection of street lamps However, this kind of street lamp control mode can not realize the intelligent urban lighting [14][15]; the relevant Japanese technical personnel developed the intelligent street lamp based on the HBS related protocol, which solved the intelligent lighting from the terminal, but it could not effectively match with the lighting system [16][17][18]. In terms of the construction of smart lighting system, France, as the first country to operate smart lighting system, uses power carrier technology and GPRS wireless communication technology to control the lighting equipment of each node in the city, and its corresponding lighting system reflects a certain degree of intelligence [19][20][21]; related countries in Eastern Europe adopt a large number of LED lighting technology in the design of smart city lighting system At the same time, solar panels, remote infrared cameras and wireless transmission technology are widely integrated into the corresponding lighting systems.…”

Section: Introductionmentioning

confidence: 99%

Intelligent Control of Urban Lighting System Based on Video Image Processing Technology

Chun-lin

2020

IEEE Access

View full text Add to dashboard Cite

The rapid iterative development of information technology, computer technology and Internet of things technology promotes the construction of smart city, and the related concepts of smart city gradually move from theory to practice. As an important part of the development of smart city, the intelligent lighting and intelligent control of urban lighting system become increasingly urgent with the development of the latest Internet of things technology and video image processing technology. Based on the current Internet of things data communication and related processing technology as the background, this paper constructs the overall control model of smart city lighting system, including GPRS wireless transmission technology and ZigBee technology. In the core algorithm, this paper innovatively presents an improved video image processing technology based on Gaussian mixture algorithm, which mainly describes the background of a specific scene in multi-dimensional model, so as to improve the reliability of the whole scene judgment. At the level of noise suppression, the video image processing algorithm proposed in this paper designs interference noise suppression technology based on the principle of mean filtering, so as to achieve the accuracy and integrity of urban traffic scene extraction. In order to solve the security problems of the whole video image processing technology in information extraction, storage and analysis, this paper adds the electromagnetic information leakage prevention algorithm in the video image processing technology, which mainly processes the video image at the source, so as to reduce the electromagnetic radiation of the overall information. Based on this, this paper completed the construction of the software and hardware of the city intelligent lighting system. On this basis, the software and hardware construction of urban intelligent lighting system is completed. At the same time, the experiment was carried out in a small-scale scene of a city. The experimental results show that the intelligent urban lighting system based on video image processing technology is feasible and can achieve the desired effect. At the same time, the lighting energy consumption level can be reduced by about 30%, and the corresponding failure rate can be reduced by about 30%. INDEX TERMS Video image processing technology; smart city; Internet of things technology; noise suppression; information leakage prevention technology;

show abstract

A robust butt welding seam finding technique for intelligent robotic welding system using active laser vision

Cited by 53 publications

References 31 publications

A Weld Position Recognition Method Based on Directional and Structured Light Information Fusion in Multi-Layer/Multi-Pass Welding

A Weld Position Recognition Method Based on Directional and Structured Light Information Fusion in Multi-Layer/Multi-Pass Welding

A High-Performance Deep Learning Algorithm for the Automated Optical Inspection of Laser Welding

Intelligent Control of Urban Lighting System Based on Video Image Processing Technology

Contact Info

Product

Resources

About