Integration of Visual Information and Robot Offline Programming System for Improving Automatic Deburring Process

Lai, Zengliang; Xiong, Rentao; Wu, Hongmin; Guan, Yisheng

doi:10.1109/robio.2018.8665148

Cited by 13 publications

(16 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…If, on the other hand, the feed rate is too high, the tool can be unable to remove the burr. Methods have been proposed to adjust the feed rate based on burr height (Lai et al, 2018;Xiong et al 2018), where the feed rate is adjusted based on given burr height thresholds.…”

Section: Adjusting Feed Ratementioning

confidence: 99%

Automated 3D burr detection in cast manufacturing using sparse convolutional neural networks

et al. 2022

View full text Add to dashboard Cite

For automating deburring of cast parts, this paper proposes a general method for estimating burr height using 3D vision sensor that is robust to missing data in the scans and sensor noise. Specifically, we present a novel data-driven method that learns features that can be used to align clean CAD models from a workpiece database to the noisy and incomplete geometry of a RGBD scan. Using the learned features with Random sample consensus (RANSAC) for CAD to scan registration, learned features improve registration result as compared to traditional approaches by (translation error ($$\Delta $$ Δ 18.47 mm) and rotation error($$\Delta 43 ^\circ $$ Δ 43 ∘ )) and accuracy(35%) respectively. Furthermore, a 3D-vision based automatic burr detection and height estimation technique is presented. The estimated burr heights were verified and compared with measurements from a high resolution industrial CT scanning machine. Together with registration, our burr height estimation approach is able to estimate burr height similar to high resolution CT scans with Z-statistic value ($$z=0.279$$ z = 0.279 ).

show abstract

Section: Adjusting Feed Ratementioning

confidence: 99%

Automated 3D burr detection in cast manufacturing using sparse convolutional neural networks

et al. 2022

View full text Add to dashboard Cite

show abstract

“…A vision system is used to recognise the edges of the workpiece. Like with the CAD/CAM method, the outline formed by the edges of the workpiece become the deburring path [8], [9].…”

Section: Deburring Pipelinementioning

confidence: 99%

“…In [8], a vision-assisted robot offline programming system has been developed. The edges of the workpiece used for testing are all straight.…”

Section: Sensor-based Path Generationmentioning

confidence: 99%

Deburring Using Robot Manipulators: A Review

Onstein

Semeniuta

Bjerkeng

2020

2020 3rd International Symposium on Small-Scale Intelligent Manufacturing Systems (SIMS)

View full text Add to dashboard Cite

Deburring of cast parts can be a very challenging task. Today, large burrs on large casting are mostly removed manually. Workers are exposed to hazardous working conditions through, among other things, high noise and vibration levels. Special purpose CNC-machines are available for deburring tasks, but they have a high investment cost that makes them unfit for high-mix low-volume processes. Deburring with robot manipulators are seen as a suitable and less expensive alternative, and have been in the focus of research topic for the last 50 years. Unfortunately, it has failed to move from research into industrial applications. One reason is the long system setup time that makes the cost of automatic deburring too high. This paper deals with the status and usage of robot manipulators in deburring applications with a focus on solutions for cast parts. The deburring pipeline and its components are investigated. There is a special focus on the solutions that lead to a more flexible and automatic deburring system by using sensors such as laser, vision and force control. The solutions are evaluated with regards to the current challenges with robotic deburring and what needs to be improved for robotic deburring to become available for high-mix low-volume processes.

show abstract

“…The continuous reduction of production and project time in the conditions of current automated systems requires the use of offline programming of industrial robots [5]. These methods can provide solutions for the integration of models of real devices, for finding appropriate solutions, whether for the layout of workplaces, the range of robotic arms and possibly for testing the technologies avoiding the installation of a real robotic cell [6,7].…”

Section: Introductionmentioning

confidence: 99%

The Role of a Behavioural Model for the Virtual Commissioning of Robotic Manufacturing Systems

Skýpala

Ružarovský

2022

Research Papers Faculty of Materials Science and Technology Slovak University of Technology

View full text Add to dashboard Cite

This paper focuses on virtual commissioning of a robotic manufacturing system, its theoretical background, and an analysis of its importance in the design of automated and robotic systems. Virtual commissioning allows the PLC control program to be tested and debugged on a created digital model of the machine, called a digital twin of the machine. Just this solution can simulate and optimize the automated system design itself without the need to have real hardware (PLC, automation elements, or the whole machine/equipment). Virtual commissioning offers an effective alternative to reduce the risks and effort of real commissioning of the machine. This makes it possible to reduce the time to market and increase flexibility, efficiency, and quality. Virtual commissioning in a single-control system is a simple solution; we can either use the Software-in-the-Loop method with emulated PLC control, simulated behavioural model, and co-simulation model or Hardware-in-the-Loop method with real controller. The problem appears when we have various types of controller, including an industrial robot controller. The paper deals with the theoretical background and partial outlines of solutions in the use of different types of the control system, if interconnections or emulators for different control systems are available. The recommended solution is to use a separate solution for the 3D simulation of the robotic system and an independent solution for the behavioural model, which will be tested in the future.

show abstract

Integration of Visual Information and Robot Offline Programming System for Improving Automatic Deburring Process

Cited by 13 publications

References 13 publications

Automated 3D burr detection in cast manufacturing using sparse convolutional neural networks

Automated 3D burr detection in cast manufacturing using sparse convolutional neural networks

Deburring Using Robot Manipulators: A Review

The Role of a Behavioural Model for the Virtual Commissioning of Robotic Manufacturing Systems

Contact Info

Product

Resources

About