The current industrial scenario is turning into nothing less than the fourth industrial revolution. And it is increasingly characterized by companies that adopt solutions in line with the technological progress in their fields. In particular, devices are now being installed and integrated in manufacturing sites in order to facilitate interconnection and dialogue between plants: this allows companies to exercise ongoing control of production dynamics, not to mention optimize the different steps of the manufacturing process.
At the heart of this evolution lies the continuous exchange and efficient management of data, which, with the adoption of AI (Artificial Intelligence) techniques, will soon become an integral part of formalized models that can act as expert systems and decision support systems. What’s more, these solutions are able to self-regulate in order to avoid an excess of input and output data; on top of that, they can also integrate data coming from research and development departments. Thus, thinking and moving in a 4.0 world means much more than investing in robotics or process automation: indeed, it requires an integrated vision throughout the entire value chain. The Cavagna Group’s manufacturing companies have been involved in this evolution for a long time, as proven by specific examples of innovation that have been seen along the way. Three interesting cases are provided by the Omeca departments.
First of all, Omeca technicians carried out a specific study of internal processes to determine which aspects could benefit most directly from industry 4.0 upgrades. That led them to develop a data collection system for the turning process. They were able to integrate this innovative solution with the system that currently collects and stores the information in a database. The next big step is to install additional sensors in order to calculate energy use in the industrial motors. At that point, the entire data flow will go through a data analysis system in order to identify the correlation between environmental variables, energy use and physical parameters as detected by the industrial machinery itself. This procedure will allow Omeca to adopt predictive maintenance systems, replacing or supplementing current preventive models. This project is on the verge of being finalized. Another very interesting project at Omeca is based on the use of sensors that calculate electric energy consumption and then feed the data into an intranet dashboard (which also reports the same technical features mentioned in the project above). The goal is also to aggregate the data once they have been collected (this analysis has already been performed and is in its formalization phase). In a third project-complementary to the previous ones-the Omeca staff is evaluating data collection from work machines in order to restore process data, create a data history and then carry out checks, aggregation and analyses. Again, the goal is to implement effective predictive maintenance techniques and achieve better energy management. This project is in the start-up phase.
