PREMANI

Design, development and implementation of Digital Manufacturing solutions for Quality Prediction and Intelligent Maintenance

The development of high efficiency production systems that allow to minimize production costs, improve productivity and product quality is universally recognized as one of the central themes of Smart Manufacturing, particularly in the vision of Industry 4.0.

High production efficiency is a necessary condition for the competitiveness of all companies, which must achieve an improvement in performance, and achieve an element of differentiation from low-cost countries through the production of high-quality products. This aspect is particularly significant for the Venetian production system.

In addition, systems with high application flexibility allow to maintain their efficiency even in the face of extreme variability in demand, and at the same time to achieve a reduction in waste (also in terms of environmental sustainability) and energy consumption from inefficient processes (energy efficiency).

In this perspective, it is necessary to develop methodologies, technologies and integrated tools for maintenance, quality control, and production logistics. The Premani project aims to demonstrate the ability of these techniques to penetrate heterogeneous application areas, characterized by very different needs, leveraging on methodological aspects of a general nature.

The project aims to develop techniques that can address the issue of predicting the operating characteristics of machines and plants, combining the analysis of quality (of the product) with that of efficiency (of plants), in a context that is then described as Predictive Manufacture.

The solutions developed belong to the field of Digital Manufacturing, providing the realization of advanced tools for decision support, and hardware-level components (dedicated sensor architectures, low-cost embedded systems for real-time use of complex forecasting models), infrastructure (cloud-based IT platforms), and algorithms (with particular emphasis on machine learning techniques).