Mission

The REFIMAN project aims to create a hardware-software platform for the retrofitting and revamping of non-sensorized industrial plants with the aim of giving them smart and i4.0 characteristics

The system will be based on diagnostic/prognostic techniques coupled with a Machine Learning algorithm with self-learning capabilities

Thanks to the ability of the retrofitting system to carry out timely control of production quality, it will be possible to identify products out of tolerance before they undergo subsequent processing and the finished product is reached.

In this way, if the retrofitting system proves effective, a decrease in the percentage of finished products that are discarded because they do not comply with the quality inspection carried out before being put on sale is expected.

As a result,

it will be possible to avoid unnecessary processing on products already destined to be discarded, thus streamlining the use of energy resources throughout the entire production process.

In terms of costs, and as the literature suggests, the cost of maintenance in manufacturing companies would exceed 15% of the total costs (Salonen and Deleryd, 2011). Maintenance costs can concern direct costs (labour, material) and indirect costs due to non-conformity products and rejected products. On average, indirect maintenance costs are 24% of total maintenance costs.

The project aims to reduce discarded products and contribute to the circular economy.

The percentage of improvement will depend on the state and type of the machinery.