Starting date : Nov. 2018 > Oct. 2020
Lifetime: 36 months
Program in support : H2020-FoF-09-2017Industry 2020 in the Circular Economy
Status project : complete
CEA-Leti's contact :
Tristan Caroff
Bernard Strée
Project Coordinator: Linnaeus University (SE)
Partners: - DE: Bosch Rexroth, Overbeck, Technical University of Chemnitz, Technical University of Munich
- EL: Paragon
- ES: Goma-Camps, Ideko, Itmati, Lantier, Sakana, Savvy, Soraluce
- FR: CEA-Leti, Vertech Group
- SE: E-Maintenance, Lineaus University
- SK: Spinea
Target market: n/a
Publications:
Investment: € 7.3 m.
EC Contribution: € 6.1 m.
| Stakes
CEA-Leti’s major role in the PreCoM project is to specify and develop a wireless multisensor platform. This platform will provide additional data (measurements) on machine tool equipment and assets, which will then be combined with production and maintenance data to enable a PreCoM disruptive maintenance approach to damage localization and prediction.
The main challenge for CEA-Leti is to develop long-lasting wireless sensor nodes to collect data as close as possible to critical moving parts in a harsh industrial environment.
Machine-tools are associated with harsh environments integrating moving parts, metallic structures and liquid cooling that can cause masking during Radio Frequency communication as well as strong vibrations. During the first year of the PreCoM Project, CEA-Leti has set up a preliminary communication node based on a Bluetooth Low Energy (BLE) toolkit. This preliminary node has been designed to overcome the technological limitations on wireless communication in a machine-tool environment. This node is associated with a wireless gateway, based on an embedded Linux microcomputer, for collecting the data through BLE. The wireless communication building block of the sensor node has been validated under real machining conditions (liquid coolant, hot chips, dynamic cutting, etc.) in collaboration with IDEKO provided by the Danobat Group, a PreCoM project partner.
Cheaper, more powerful sensors and big data analytics offer an unprecedented opportunity for monitoring machine-tool performance and health. However, manufacturers only spend 15% of their total maintenance costs on predictive (unlike reactive or preventive) maintenance. The aim of the PreCoM project is to deploy and test a predictive cognitive maintenance decision-support system capable of identifying and localizing damage, assessing damage severity, predicting damage evolution, assessing remaining asset life, reducing the probability of false alarms, providing more accurate failure detection, issuing orders to conduct preventive maintenance actions and ultimately increasing machine in-service efficiency by 10% or more. The platform features four modules: a data acquisition module leveraging external sensors and sensors directly embedded in machine-tool components; an artificial intelligence module combining physical models, statistical models and machine-learning algorithms capable of monitoring individual health and supporting multiple assets and dynamic operating conditions; a secure integration module connecting the platform to production planning and maintenance systems via a private cloud and providing additional safety, self-healing and self-learning capabilities and a human interface module including production dashboards and augmented reality interfaces for facilitating maintenance tasks. The project consortium includes three end-user factories, three machine-tool suppliers, one leading component supplier, four innovative SMEs, three research organizations and three academic institutions. Together, the team intends to validate the platform across a broad spectrum of real-life industrial scenarios (low volume, high volume and continuous manufacturing) and demonstrate the platform’s direct impact on maintainability, availability, work safety and costs to document results in detailed business cases for widespread industry-wide dissemination and usage.
IMPACT
Business impact. Predictive maintenance solutions are a key driver of the Industry 4.0 revolution. Manufacturers are seeing maintenance as a strategic business function as they seek to reduce maintenance costs and downtime, and increase asset lifecycles. The primary objective of the PreCoM solution is to increase in-service machine-tool efficiency. Knowledge impact. By merging knowledge from different areas of expertise (sensors, statistics, maintenance, production planning, artificial intelligence, augmented reality), the PreCoM project aims to create new global knowledge of Predictive and Cognitive Maintenance.
|
|