• Rahul Vishnoi

Automatic process modelling (APM) is an enabling technology for the development of smart fabrication systems (IMSs). The analysis of obtained models enables the prompt identification of error-prone measures and the design of effective mitigation strategies, from parameter optimization to the production of tailored staff training, in all aspects of the manufacturing process. In this work as propose a Time Delay Neural Network (TDNN) applied to low-level data for the automatic recognition of various process phases in collaborative industrial tasks. As selected TDNN because, while retaining computational performance, they are suitable for modelling time dependent processes over long sequences. As acquired two novel datasets reproducing a standard IMS environment to experimentally evaluate the recognition efficiency and the generalization capability of the proposed process. Datasets (including manually annotated ground-truth labels) are publicly accessible to allow other methods to be evaluated on them, replicating a standard environment for Industry 4.0. The first dataset replicates a collaborative robotic system in which a human operator communicates with a robotic manipulator while performing a pick and place function. The second package is a human tele-operated, aided robotic manipulation for assembly applications. The results obtained are superior to other literature methods, and indicate an improved computational efficiency.

Intelligent manufacturing, Industry 4.0, Time delay neural network, TDNN, Collaborative Robot.

"Automatic Time-Lapse Neural Network Modelling Based On Low-Level Data", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.6, Issue 6, page no.744-749, June-2019, Available :http://www.jetir.org/papers/JETIREY06139.pdf

"Automatic Time-Lapse Neural Network Modelling Based On Low-Level Data", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.6, Issue 6, page no. pp744-749, June-2019, Available at : http://www.jetir.org/papers/JETIREY06139.pdf