首页|New Robotics Findings from Science University of Malaysia Described (Acoustic Signal-based Automated Control of Welding Penetration Using Digital Twin Technology)

New Robotics Findings from Science University of Malaysia Described (Acoustic Signal-based Automated Control of Welding Penetration Using Digital Twin Technology)

扫码查看
Researchers detail new data in Robotics. According to news reporting originating from Pulau Pinang, Malaysia, by NewsRx correspondents, research stated, “Weld penetration control has emerged as a critical area of research in the field of online control for ensuring the quality of robotic welds. Acoustic signals, which are known for their distinct temporal characteristics, play a pivotal role in the online assessment of weld quality.” Financial support for this research came from Ministry of Higher Education Malaysia under Fundamental research grant scheme (FRGS). Our news editors obtained a quote from the research from the Science University of Malaysia, “This study proposes a novel filter bank specifically tailored for robotic welding and investigates the working environment of robot welding. Twenty-six time-domain and frequency-domain features were extracted from weld acoustic signals, and statistical analyses and comparative methods were used to identify variations in defective signal features and interpret their physical significance. By leveraging these acoustic signal characteristics, this study established a predictive identification model and an online feedback controller. The predictive identification model effectively identified different penetration levels in the welding process, and the identification results served as a reference input for online regulation of the welding speed by the controller. Additionally, a digital twin system was developed, where the identification model and controller functioned as digital objects on a computer and an edge computer, respectively. Experimental tests demonstrated the superior performance of the system and model in accurately reflecting welding process penetration, regulating and stabilising the welding speed, and significantly enhancing the welding quality.”

Pulau PinangMalaysiaAsiaEmerging TechnologiesMachine LearningRoboticsRobotsTechnologyScience University of Malaysia

2024

Robotics & Machine Learning Daily News

Robotics & Machine Learning Daily News

ISSN:
年,卷(期):2024.(Feb.19)
  • 35