The Lighthouse Plant project: Digitization & Predictive Mainenance
- Analytics & Modeling - Digital Twin / Simulation
- Analytics & Modeling - Machine Learning
- Automation & Control - Programmable Logic Controllers (PLC)
- Functional Applications - Enterprise Resource Planning Systems (ERP)
- Equipment & Machinery
- Discrete Manufacturing
- Digital Twin
- Machine Condition Monitoring
- Predictive Maintenance
Alleantia is among the partners of Ansaldo Energia’s Lighthouse Plant project, the only one in Italy relating to an Italian company that will invest 14 million euros in a three-year industrial research and development plan based on the main digital technologies of the Industry 4.0 Plan. A project that will affect the entire manufacturing process of the two Ansaldo Energia production sites in Genoa and in which Alleantia played a fundamental role as regards the interconnection methods of the machines.
Ansaldo Energia
Ansaldo Energia
With over 175,000 MW installed in more than 90 countries and approximately 3,500 employees, Ansaldo Energia is the largest company in Italy and one of the main areas in the world for the supply, updated and service of systems and components for energy generation, as well as one of the best expressions of technology and innovative capacity in the energy sector.
Founded in 1853, it is a Finmeccanica Group company able to build turnkey power plants with the use of its own technologies and with its own integrated resources of design, construction, commissioning and assistance.
With three product lines: gas turbine, steam turbine and generators, all characterized by advanced technology, integrated to meet the most complex needs of customers in terms of efficiency, reliability and environmental impact.
The data collection of the machines made by Alleantia allows to pass the information to the SAP Leonardo platform and to provide the information that allows the Polytechnic of Milan to study the model that defines the digital Twin of the physical machine allowing precisely to identify a series of critical parts of the machine and on these a series of clinical variables worthy of a monitoring that can allow some machine and learning algorithms to provide the system with feedback, i.e. information of malfunctions or drift of the product quality of the machine itself that with a period adequate allow to give vital information to the operator and to prevent machine downtime and malfunction problems.
Related Case Studies.
