292
D. Mishra et al.
8.4.6 Discussion
The case study presented above is a step towards automation of the FSW process. The
developed architecture predicts the weld quality, i.e. tensile strength of the weld in
real time, and controls the quality, if it is found deviating from a reference standard.
The developed architecture will help industry by eliminating the rejection of material.
More quality measuring parameters such as grain size and hardness for assessing the
quality of the weldment can be introduced in the architecture, depending upon the
application of the welded joint. Different parameters may require different signals
as a typical signal may capture a characteristic more proficiently than other. As
such, different signal processing techniques may be required to derive the useful
information from the signals. To implement Industry 4.0, the foundation lies in the
utilization of sensor and proper signal processing techniques at the pinnacle for
deriving the useful information.
8.5 Conclusion
This chapter attempted to review the evolution of all the four industrial eras, right from
Industry 1.0 to Industry 4.0. This provided critical insights on the future potential
of Industry 4.0 to attain manufacturing excellence. It is important to identify the
optimal process parameters for every manufacturing process for the elimination of the
production bottlenecks. Further, it is also crucial to constantly monitor the machines
operating at the shop floor to gain a sense of control. This chapter provides a holistic
view of how the digital tools of Industry 4.0 can aid in monitoring and control of a
welding technique. The case study in this chapter can be extended by introducing
other disturbances in the process, and finding ways to eliminate them in real time.
Over time, the underlying concepts highlighted in this chapter can be generalized
with subsequent research on various manufacturing processes.
Acknowledgements and funding This chapter is an outcome of the project funded by the Department of Heavy Industry under the Ministry of Heavy Industries and Public Enterprises, Government
of India and TATA Consultancy Services (Grant No: 12/4/2014—HE&MT).
References
1. Roy RB, Mishra D, Pal SK et al (2020) Digital twin: current scenario and a case study on
a manufacturing process. Int J Adv Manuf Technol. https://doi.org/10.1007/s00170-020-053
06-w
2. Lee J, Davari H, Singh J, Pandhare V (2018) Industrial Artificial Intelligence for industry 4.0based manufacturing systems. Manuf Lett 18:20–23. https://doi.org/10.1016/j.mfglet.2018.
09.002
D. Mishra et al.
8.4.6 Discussion
The case study presented above is a step towards automation of the FSW process. The
developed architecture predicts the weld quality, i.e. tensile strength of the weld in
real time, and controls the quality, if it is found deviating from a reference standard.
The developed architecture will help industry by eliminating the rejection of material.
More quality measuring parameters such as grain size and hardness for assessing the
quality of the weldment can be introduced in the architecture, depending upon the
application of the welded joint. Different parameters may require different signals
as a typical signal may capture a characteristic more proficiently than other. As
such, different signal processing techniques may be required to derive the useful
information from the signals. To implement Industry 4.0, the foundation lies in the
utilization of sensor and proper signal processing techniques at the pinnacle for
deriving the useful information.
8.5 Conclusion
This chapter attempted to review the evolution of all the four industrial eras, right from
Industry 1.0 to Industry 4.0. This provided critical insights on the future potential
of Industry 4.0 to attain manufacturing excellence. It is important to identify the
optimal process parameters for every manufacturing process for the elimination of the
production bottlenecks. Further, it is also crucial to constantly monitor the machines
operating at the shop floor to gain a sense of control. This chapter provides a holistic
view of how the digital tools of Industry 4.0 can aid in monitoring and control of a
welding technique. The case study in this chapter can be extended by introducing
other disturbances in the process, and finding ways to eliminate them in real time.
Over time, the underlying concepts highlighted in this chapter can be generalized
with subsequent research on various manufacturing processes.
Acknowledgements and funding This chapter is an outcome of the project funded by the Department of Heavy Industry under the Ministry of Heavy Industries and Public Enterprises, Government
of India and TATA Consultancy Services (Grant No: 12/4/2014—HE&MT).
References
1. Roy RB, Mishra D, Pal SK et al (2020) Digital twin: current scenario and a case study on
a manufacturing process. Int J Adv Manuf Technol. https://doi.org/10.1007/s00170-020-053
06-w
2. Lee J, Davari H, Singh J, Pandhare V (2018) Industrial Artificial Intelligence for industry 4.0based manufacturing systems. Manuf Lett 18:20–23. https://doi.org/10.1016/j.mfglet.2018.
09.002