High added-value products manufacturing methods are undergoing a continuous evolution nowadays, aiming to get higher productivity rates, product quality and reduction of defective products. Manufacturing companies increasingly use condition monitoring solutions and Predictive Maintenance (PdM) solutions to guarantee the intended usage of production equipment and to avoid unplanned downtimes. As such, this white paper presents a review of the lessons learned from the point of view of six EU funded H2020 research projects (PRECOM, PROPHESY, PROGRAMS, SERENA, UPTIME and Z-BREAK), funded under the topic “FOF-09-2017 - Novel design and PdM technologies for increased operating life of production systems”. These projects were active from 2017 to 2021 and together constituted the ForeSee cluster. Research and technology partners together with industrial end-users worked collaboratively to develop and deploy solutions that advance maintenance practice in industry towards more efficient, sustainable, human-centric and resilient factories. This white paper aims to share knowledge, vision and lessons learnt by ForeSee cluster partners on the topic of PdM, as well as to provide recommendations for advancing PdM in industrial practice. The core target groups of this report are industry practitioners, people in academia and policy makers at the local, national and EU levels.  The technologies that have acted as key-enablers in several of the ForeSee cluster projects (such as Internet of Things, Digital Twin, Proactive Computing, Virtual/Augmented Reality and linked data) are discussed in this document. Furthermore, the skilling of personnel, as well as the use of standardized technologies and processes are cross-cutting issues pertinent to ForeSee projects and their role in PdM projects is presented. The evaluation of these concepts and technologies in ForeSee industrial cases has proven their significance to industrial practice. The validation phase in industrial cases has served the ForeSee cluster with the provision of the following lessons learnt and recommendations for successful adoption of technology and best practices.  

Lessons learned:

✓ Need for the development of structured data repositories with Industry4.0 and PdM datasets  

✓ Availability for testbeds for PdM, condition-based maintenance and intelligent asset management

✓ Adjustment of AI-based Maintenance and Asset Management Systems to facilitate accessibility by the non-experts

✓ Standardization, data and semantics interoperability, as necessary enablers to support the diverse software, hardware as well as business process landscape in asset management. Recommendations

✓ Business models for Condition Based Maintenance and Intelligent Asset Management should be further investigated

✓ Mobile Management - Mobile-First Condition Based Maintenance are important concepts that could benefit the adoption of CBM and PdM strategies  

✓ Smart and Autonomous Objects should be further considered when it comes to data collection, inspection, data collection and communication.  

✓ Adequate actions for Training - Education - Lifelong Learning of people working closely with advanced data and Internet of Things technologies should be considered.  (21) (PDF) Predictive maintenance technologies for production systems. A roadmap to development and implementation.