Manufacturing accounts for 15.96% of EU GDP (World Bank), is undergoing immense yet gradual Industry 4.0 transformation with the help of advancements including predictive maintenance, whose market size is estimated to be worth USD 4.9b by 2021 (Markets and Markets).
SMART-PDM’s objective is to acquire manufacturing data to provide diagnosis and prognosis information while rendering the underlying technology financially feasible.
In order to achieve this goal, we created a very complementary and conducive consortium with 12 use case demonstrators ambitious to see the trial results, 9 integration & tools providers and 9 technology and knowledge providers all waiting to test out and further improve their technologies, all with a balanced breakdown of 11 SMEs, 10 Large Enterprises and 4 RTOs which are spread across 5 countries.
The innovative aspects of SMART-PDM will include:
- a revolutionary new philosophy where various solutions will compete with each other in order to improve the Overall Equipment Effectiveness (OEE), a metric that takes into account the availability, performance and quality of the machines in the production system. SMART-PDM places a substantial effort to improve this key figure. The aim of the project is to develop completely automatic condition based approach that increases OEE at least 20% from 60% to 80% in European industry. This kind of self-developing diagnostics and prognostics allows machines or processes to keep themselves in good condition by themselves and give precise knowledge of the failures and instructions how to maintain the condition or repair them.
- the use of low-cost printed sensors thanks to a negative Moore’s law, automatic connecting sensors and automatic diagnostics, and prognostics including attribute selection
- looking out for financial feasibility of PdM, by developing ways in which all costs of acquiring attributes and a target prediction quality being numerically mapped to monetary terms, therefore forming an understanding of what processes and equipment are worth monitoring financially. Briefly speaking, this can be done by use of machine learning and optimisation techniques to perform state estimation and simulate prediction quality based on inferred states, all in order to make financial decisions for maintenance investments. A corollary will be the automatic and smarter identification of sensor breakage.
- technical compliance with CSN EN 13306 – Maintenance, ISO 13374-1 and 13374-2.
There are substantial overall technical outcomes and commercial benefits, which are reconciled by this project: There will besavings in cost of maintenance, waste and parts as well as improvements in quality and throughput. The technological advancements validated by the demonstrators will help enhance the know-how, technologies, solution offerings and toolsets of the corresponding partners, which then will have a positive impact on a same market vertical as well as on other horizontal markets.