Predictive maintenance in industry 4.0

One of the biggest advantages of Internet of Things (IoT) for manufacturers is that it allows them to adopt a smarter approach. The continuous analysis of assets’ behavior data improves their efficiency, but there is also another important aspect: it helps to predict product failure and increases assets’ uptime.

Surely maintenance is a strategic concern in manufacturing; however, a third of current maintenance activities are carried out ineffectively. IoT can come to the aid: predictive maintenance has become a top business objective for innovative manufacturers. (www.smartindustry.com/).

On 7th July, Ecipa Scarl participated in an interesting webinar about Predictive Maintenance in Industry 4.0, organized by MADE, a Competence Center for Industry 4.0 managed by the Polytechnic University of Milan (Italy).

Predictive maintenance builds on activity planning based on a dynamic model of a component, which allows determining the best strategy to put in place for the component itself.  Data collection and analysis are therefore at the core of predictive maintenance.

Predictive maintenance offers several benefits. It reduces maintenance costs (down by 50%), unexpected failures (down by 55%), repair and overhaul time (down by 60%) and spare parts inventory (down by 30%); it increases by 30% machinery mean time between failures and uptime.  (reliabilityweb.com/)

Of course, predictive maintenance requires many efforts, in terms of time and resources; therefore, it is not always the best solution. Advantages and benefits have to be carefully considered, and predictive maintenance has to be compared to other strategies of maintenance (for example reactive maintenance).  Among the parameters to be taken into account there are the value of the component, the impact its failure would have on production, the complexity of fault repair.

The webinar was especially focused on how an SME can embark on the journey towards predictive maintenance. Deep knowledge of its own assets is definitely the starting point, as it allows the company to determine which are the most critical assets, and if any data collection is already in place and/or it is a viable option. The study of representative cases is fundamental too. Undoubtedly, skills and competencies are required, not only at the technical level but also as a capacity to look at the bigger picture, to examine the system as a whole: a multidisciplinary approach is a key to success.

Comments are closed.