首页|New Machine Learning Study Findings Recently Were Reported by a Researcher at Po lytechnic University Torino (Fault Prediction in Resistance Spot Welding: A Comp arison of Machine Learning Approaches)
New Machine Learning Study Findings Recently Were Reported by a Researcher at Po lytechnic University Torino (Fault Prediction in Resistance Spot Welding: A Comp arison of Machine Learning Approaches)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
A new study on artificial intelligence is now available. According to news reporting from Torino, Italy, by NewsRx jou rnalists, research stated, "Resistance spot welding is widely adopted in manufac turing and is characterized by high reliability and simple automation in the pro duction line." Funders for this research include Project Manage 5.0. The news correspondents obtained a quote from the research from Polytechnic Univ ersity Torino: "The detection of defective welds is a difficult task that requir es either destructive or expensive and slow nondestructive testing (e.g., ultra sound). The robots performing the welding automatically collect contextual and p rocess-specific data. In this paper, we test whether these data can be used to p redict defective welds. To do so, we use a dataset collected in a real industria l plant that describes welding-related data labeled with ultrasonic quality chec ks. We use these data to develop several pipelines based on shallow and deep lea rning machine learning algorithms and test the performance of these pipelines in predicting defective welds. Our results show that, despite the development of d ifferent pipelines and complex models, the machine-learning-based defect detecti on algorithms achieve limited performance."
Polytechnic University TorinoTorinoI talyEuropeCyborgsEmerging TechnologiesMachine Learning
NETL
NSTL
