Use of NDT data to enable factory transformation
Abstract
Industry 4.0 is an all-encompassing concept that covers many aspects of improving a factory. It can be summarised by two aspects: the utilization of microprocessors imbedded within factory systems, which enable the convergence of the physical and virtual world in the form of cyber physical systems; to network such systems with other resources to create the "Internet of things” (IoT).
There are two potential areas that have been identified for utilization of NDT within an industry 4.0 context. Firstly, since NDT data gives information about part quality, it can be used to the advantage of cyber physical systems linked with the IoT, where they can be used to inform the concessions processes and potentially aid design/stress optimisation. Another consideration is the use of autonomous process control through machine learning, for example "Automated Defect Recognition”, which will streamline the evaluation process.
There are also challenges ahead that will need to be overcome to enable the use of NDT data for factory transformation. The first challenge would be the wider use of automation in NDT processes; many NDT processes are still evaluated manually, where data is not captured. Next, data standardisation will be important to allow systems to communicate effectively. The final and more difficult aspect to quantify will be a cultural shift. NDT has been seen as a non-value added process within a factory environment. The attitude shift would be to view NDT as a benefit, aiding cyber physical systems embedded within an advanced factory system.
There are two potential areas that have been identified for utilization of NDT within an industry 4.0 context. Firstly, since NDT data gives information about part quality, it can be used to the advantage of cyber physical systems linked with the IoT, where they can be used to inform the concessions processes and potentially aid design/stress optimisation. Another consideration is the use of autonomous process control through machine learning, for example "Automated Defect Recognition”, which will streamline the evaluation process.
There are also challenges ahead that will need to be overcome to enable the use of NDT data for factory transformation. The first challenge would be the wider use of automation in NDT processes; many NDT processes are still evaluated manually, where data is not captured. Next, data standardisation will be important to allow systems to communicate effectively. The final and more difficult aspect to quantify will be a cultural shift. NDT has been seen as a non-value added process within a factory environment. The attitude shift would be to view NDT as a benefit, aiding cyber physical systems embedded within an advanced factory system.
