Monitoring of the Friction Stir Welding Process: Upgrading Towards Industry 4.0

Introduction

The term Industry 4.0 is defined in number of ways by different organizations and industry experts which is generally used as a notation for fourth industrial revolution. One such definition for Industry 4.0 is utilizing information and communication technology (ICT) for smart networking of machines and processes for industry. By this view it can be stated that the process and machines are networked and can communicate together that leads to novel routes of manufacturing, value addition and concurrent process optimization. The advancements in ICT tool technologies makes possibilities for smart industries. These tools are almost similar to the tools used in Industrial Internet of Things (IIOT) for tracking and remote monitoring like purposes. Industry 4.0 can also be stated as the name used for exposing the present development in data communication and automation in manufacturing that consists of various ICT tools such as cyber-physical systems, the Internet of things, cloud computing and cognitive computing in road to developing the smart factory (Pires, Cachada, Barbosa, Moreira, & Leitão, 2019).

Industry 4.0 proposes more industrial automation when compared to third revolution and also tries to bridge the gap between digital and physical world all the way through cyber-physical system, facilitated by IIoT. It also shifts to the system where smart products or devices make the decision on production process instead of traditional central industrial control system. Further it proposes closed-loop data forms and control systems and enables more customization of products (Cao, Giustozzi, Zanni-Merk, de Bertrand de Beuvron, & Reich, 2019). Overall, it can be stated as the system/model that aims to facilitate the automatic decision making, synchronized asset and process monitoring and also facilitates all the stakeholders to involve in value addition at the earlier part of the process through networking.

At present, the Industry 4.0 is really revolutionizing the entire industrial sector and it transformed the approach industries used to produce, enhance and dispense their products. Many industries integrated the Industry 4.0 facilitating technologies such as IoT, cloud computing, AI and machine learning into their various sections of operations and some industries implemented in all sections of their facility. These industries utilize different kind of sensors, software and robotic tools for data collection & analysis, decision making and concurrent rectification (Chen, Han, Cao, Zheng, & Xu, 2020). It is used for factory automation, predictive maintenance, optimization and process enhancement and all are in single focus of customer satisfaction.

This advanced concept also reduces machine down time by initiating predictive maintenance based on the continuous data collected from the shop floor and also helps in real time visibility of machine performance (Dinardo, Fabbiano, & Vacca, 2018). Utilization of Artificial Intelligence based quality assessments instead of manual checkup results in greater product quality. remote monitoring of process flow and machine performance also an added advantages of this concept and it is possible to detect errors in any part of production or machine in quick time with the aid of machine learning concepts which will protect the machine break down and saves lot of wealth (Farahani et al., 2019).

Friction Stir Welding (FSW) is new and advanced solid state welding technique developed by The Welding Institute in 1991. Since its inception, the technique has been widely employed in many type of industries, majorly in automobile and aerospace industries. In Industry 4.0 context, the basic building block is data and without enough data the process cannot be adoptable to smart factory. In order to make the FSW Industry 4.0 ready process, different sensors are implemented in existing FSW machine (Mishra et al., 2020). The valuable information collected from sensors can be utilized for precise control of the process.