Maintenance methodologies and approaches based on intelligent data processing techniques are crucial when improving productivity and reducing machine stoppages, but also in order to avoid expensive repair costs. Detection of potential failure and the corresponding corrective maintenance are well established and accomplished, but predictive maintenance derived from a correct failure prediction is not yet a reality.
Intelligent methods for collecting and organising data (e.g. Artificial Intelligence and Data Mining) will provide new concepts of advanced maintenance addressing flexibility, easy integration in production environments and easy to interpret recommendations and results. By combining different sources of process data coming from advanced embedded information devices, the knowledge inferred from production equipment will be reinforced and reused in the maintenance learning/training process. These techniques will also provide a useful decision making support tool based on optimal planning and scheduling of maintenance operations in order to optimise the energy consumption.
Research activities should address all of the following areas:
- Developing R&M (Reliability & Maintainability) design practices/methods (including organisation) to predict and assess the availability of equipment during production already at an early design stage;
- Developing and integrating of advanced and generic embedded information devices designed to capture relevant information, with data pre-processing capabilities (sensors,
ambient intelligence devices, RFID tags etc);
- Defining new algorithms and techniques based, for example, on Artificial Intelligence and Data Mining methodologies, in order to provide intelligent data processing and
knowledge extraction from information gathered from production equipment and in order to integrate knowledge reuse into production.
By improving predictive maintenance, the lifetime of the system and the availability of the whole process will be increased. The detection of unforeseen decline on its operational life cycle, depending on process data and contextual information (operational time, number of stoppages, environmental conditions, etc), will be the key issue in maintenance tasks in order to provide a higher resistance of equipment, leading to improvements in future design of components involved in manufacturing processes.
In order to ensure an efficient implementation and maximum impact of SME-related activities, the leading role of SMEs with R&D capacities will be evaluated under the criteria 'Implementation' and 'Impact': the coordinator does not need to be an SME but the participating SMEs should have the decision making power in the project management; and the output should be for the benefit of the participating SMEs and the targeted SME dominated industrial communities.
Funding Scheme: SME-targeted collaborative projects.
Expected impact: Manufacturing companies in Europe are investing in new smart and agile maintenance approaches that may increase the lifetime and energy efficiency of the
production equipment and reduce its maintenance costs. New tools and methodologies for the sustainable maintenance of production equipment should contribute, in particular, to energy
consumption management and optimisation tools, reducing energy costs and environmental pollution by a factor of 20%. Moreover, research projects in this field should contribute to
their worldwide competitiveness and to the creation of new jobs.