Authors :
Amrathakara Bhat; Aishwarya Dhadd; Bhushan Sharad Patil; Bharani Kumar Depuru
Volume/Issue :
Volume 8 - 2023, Issue 8 - August
Google Scholar :
https://bit.ly/3TmGbDi
Scribd :
https://tinyurl.com/4trpb7jc
DOI :
https://doi.org/10.5281/zenodo.8323380
Abstract :
The research focuses on leveraging video
analytics to track the sequence followed during clamping
in the Automobile Manufacturing industry while
adhering to the principles of the Poka-Yoke system.By harnessing the power of video analytics, the
manufacturing process can be monitored and optimized
to ensure efficient clamping operations. The utilization
of video analytics enables real-time tracking of the
clamping sequence, providing valuable insights into the
production line. The ML model developed with YOLOv8
can accurately identify and analyze the clamping steps,
ensuring that they followed the correct sequence. By
adhering to the principles of the Poka-Yoke system,
which is an error-proofing method, the manufacturing
industry can significantly reduce defects and improve
overall quality. The proposed system's integration with
video analytics and ML techniques offers many
advantages, including continuous monitoring, rapid
identification of deviations, and immediate corrective
actions.The
research also explores the potential deployment of the
system in an AWS (Amazon Web Services) cloud
environment, which offers scalability, flexibility, and
efficient data processing capabilities. This cloud-based
implementation allows for seamless integration into
existing manufacturing workflows and facilitates
centralized monitoring and management. Overall, this
study presents a comprehensive approach to tracking the
clamping sequence in the Automobile Manufacturing
industry, leveraging video analytics, and adhering to the
Poka-Yoke system. The ML model developed using
YOLOv8 (You Only Look Once) / YOLO-NAS (Neural
Architecture Search) demonstrates exceptional accuracy,
paving the way for improved quality control, reduced
errors, and enhanced productivity in automotive
manufacturing processes.
Keywords :
Poka-Yoke, Automobile Manufacturing, Video Analytics, Artificial Intelligence, Total Quality Management in Manufacturing.
The research focuses on leveraging video
analytics to track the sequence followed during clamping
in the Automobile Manufacturing industry while
adhering to the principles of the Poka-Yoke system.By harnessing the power of video analytics, the
manufacturing process can be monitored and optimized
to ensure efficient clamping operations. The utilization
of video analytics enables real-time tracking of the
clamping sequence, providing valuable insights into the
production line. The ML model developed with YOLOv8
can accurately identify and analyze the clamping steps,
ensuring that they followed the correct sequence. By
adhering to the principles of the Poka-Yoke system,
which is an error-proofing method, the manufacturing
industry can significantly reduce defects and improve
overall quality. The proposed system's integration with
video analytics and ML techniques offers many
advantages, including continuous monitoring, rapid
identification of deviations, and immediate corrective
actions.The
research also explores the potential deployment of the
system in an AWS (Amazon Web Services) cloud
environment, which offers scalability, flexibility, and
efficient data processing capabilities. This cloud-based
implementation allows for seamless integration into
existing manufacturing workflows and facilitates
centralized monitoring and management. Overall, this
study presents a comprehensive approach to tracking the
clamping sequence in the Automobile Manufacturing
industry, leveraging video analytics, and adhering to the
Poka-Yoke system. The ML model developed using
YOLOv8 (You Only Look Once) / YOLO-NAS (Neural
Architecture Search) demonstrates exceptional accuracy,
paving the way for improved quality control, reduced
errors, and enhanced productivity in automotive
manufacturing processes.
Keywords :
Poka-Yoke, Automobile Manufacturing, Video Analytics, Artificial Intelligence, Total Quality Management in Manufacturing.
