EIT Digital has launched a new Innovation Activity, ALMeS (ALM-enabled Smart Maintenance), to develop a cost-effective solution based on the collection and analysis of real-time data from machines. Its Add-on, Low cost, Multi-purpose (ALM) modules for measuring real-time parameters such as vibrations, energy consumption and temperature will allow factory managers to quickly and simply optimise machinery performance and reduce costs, switching from established patterns to the more effective method of predictive maintenance.

ALMeS (ALM-enabled Smart Maintenance) is a new Innovation Activity which has been launched by EIT Digitals Digital Industry Action Line. The work will develop a cost-effective solution based on the collection and analysis of real-time data from machines. Italian company Reply will act as the Activitys business champion. Market launch is scheduled by the end of this year.

Maintenance of factory machinery is performed today mainly at fixed intervals, or on a run-to-failure basis. Real-time data from machines, that could help predict when its time for a check-up, is not usually available, as heavy sensorisation of the equipment is too expensive for most companies.
This is especially true in countries where the average company size is very small. In Italy, for instance, almost 95% of companies have less than ten employees and reduced capital expenditure capability.
Other participants in the Activity include Polytechnic of Milan, FBK, ST Microelectronics, Cohaerentia, Konux, and Crowdee as technology providers.
Its Add-on, Low cost, Multi-purpose (ALM) modules for measuring real-time parameters such as vibrations, energy consumption and temperature will allow factory managers to quickly and simply optimise machinery performance and reduce costs, switching from established patterns to the more effective method of predictive maintenance.
This change wont require huge investment: ALMeS innovative sensors are based on standard fibre optics, low-cost microcontrollers and machine-learning software. By introducing predictive maintenance methods in their plants, manufacturers could slash maintenance costs by 25%-35%, eliminate more than 70% of breakdowns and boost a 25% increase in productivity.
Customers of the new solution, which is scheduled for market launch by the end of this year, will be able to recoup the one-time fee for system implementation, plus the yearly evolutionary maintenance fee to be paid to ALMeS partners, with the savings made during the first year of usage.
Thanks to this semi-commoditised technology, the project is expected to have a significant impact in many industrial sectors with medium to high levels of automation.
Initial target sectors for the solution are likely to include the automotive industry and precision mechanics manufacturing. In a later phase, focus is likely to turn to markets which are more difficult to penetrate like the oil and gas and energy sectors, where maintenance requirements are more stringent and downtimes can heavily impact the operational costs.