Robot components show a slow degradation of their performances: data collection must begin as soon as possible. 
 

To develop and apply statistical models for supporting PdM, it is always crucial to have as much as possible failure data, which is not easy to find in the companies’ databases. Furthermore, advancing and integrating different technologies in a single automatic and digitised smart PdM system is a challenge that requires close collaboration between research and industry players. 

GESTAMP, besides getting familiar with Z-BRE4K’s solution validation and assessment methodology, got a better understanding of internal reflection and readiness to apply predictive maintenance solutions to its plants while new mitigation actions related to process flaws and defects identification were developed during the Z-BRE4K. Also, they have understood the importance of solution validation and assessment methodology defined in Z-BRE4K. 
 

SACMI-CDS found out the importance of collaboration not only with a mechanical engineering/maintenance-related professionals but also with different technical background experts that together can improve multi-tasking and combining shopfloor and office-related activities as well as scheduling of activities during the work journey.

In general, after the solution implementation (TRL5), testing the system on the shop floor (TRL6) and validation of the Z-BRE4K solution (TRL7) at end users, the very final lesson learnt can be summarised as follows:

• Live data are gathered by sensors and other systems.
• Data from individual data systems incorporated in a distributed system.
• Quality and maintenance measurements are available.
• Manual maintenance schedules are replaced with PdM procedures and schedules.
• Maintenance experts supported by gathered data and predictions to improve their know-how in the maintenance domain.
• PdM accuracy and performance is established.
• Productivity improved.
• Cost reduction obtained.
• Possibility of Testing a full end-to-end solution for maintenance management including prescriptive and predictive analytics. 
   

PHILIPS supports the idea of predictive maintenance, “listening to the machines” and understands that the key to success is close contact between technology providers and experts where data integration/architecture and machine learning are both very important projects. 
 

Quantity and quality of data need to be ensured from the beginning of the process. It is important to gather more data than needed and to have a high-quality dataset. Machine learning requires large sets of data to yield accurate results. Data collection needs however to be designed before the real need emerges. Moreover, it is important having a common ground to share information and knowledge between data scientists and process experts since in many cases they still don’t talk the same language and it takes significant time and effort from mediators to help them communicate properly. 

 

Installation of sensor infrastructure: during the initial design to incorporate the new sensors into the existing infrastructure, it is necessary to take into consideration the extreme physical conditions present inside the milling station, which require special actions to avoid sensors being damaged or falling off. A flexible approach is adopted, which involves the combination of internal and external sensors to allow the sensor network prone to less failure. Quantity and quality of data: it is necessary to have a big amount of collected data for the training of algorithms. Moreover, the integration of real-time analytics and batch data analytics is expected to provide a better insight into the ways the milling and support rollers work and behave under various circumstances. 

 

Quantity and quality of data: the available data in the FFT use case mainly consists of legacy data from specific measurement campaigns. The campaigns were mainly targeted to obtain insights about the effect of operational loads on the health of the asset, which is therefore quite suitable to establish the range and type of physical parameters to be monitored by the UPTIME system. UPTIME_SENSE is capable of acquiring data of mobile assets in transit using different modes of transport. While this would have been achievable from a technical point of view, the possibility to perform field trials was limited by the operational requirements of the end-user. Therefore, only one field trial in one transport mode (road transport) was performed, which yielded insufficient data to develop useful state detection capability. Due to the limited availability of the jig, a laboratory demonstrator was designed to enable partially representative testing of UPTIME_SENSE under lab conditions, to allow improvement of data quantity and diversity and to establish a causal relationship between acquired data and observed failures to make maintenance recommendations. 

 

• The PROPHESY-SHARE platform has developed into a multi-purpose tool for both remote support as well as providing specific work instructions and visualization of (predicted) tooling information to the maintenance mechanic. As a result, both industrial partners are considering investments in this technology.
• The end-users are very eager to work with digital support systems that ease their job as it brings a single point of data.
• Quite some hurdles to take in the field of health and safety, IT security, GDPR (e.g. face blurring).
• The development cycle with prototype demonstration v1-feedback from the end-users and other stakeholders-demonstration of an improved prototype v2-feedback from the end-users and interdepartmental stakeholders worked very well. 

• It is challenging to run a development project in a real-life production environment due to high pressure on production output.
• Data collection from legacy systems brings some specific IT challenges.
• Data understanding and data-pre-processing are crucial before starting the data analysis. 
• It was proven once more that close collaboration is needed between data scientists and process experts to get reliable results.
• The results of PROPHESY-ML application to the use cases have been reported for both demonstrators in the project’s deliverables, achieving RUL prediction with accuracy as little as 4-5% Mean Absolute Percentage error. 

Some tasks humans are good at and some they are not. Optimisation and scheduling tasks are examples of the latter. Even for the computers brute force optimisation or scheduling approach could be very difficult and require lots of computational recourses. On the other hand, there are different algorithms that can be employed depending on the problem at hand. Machining 4.0 platform demonstrator allows to experiment and demonstrate different approaches and well as scheduling problem complexity itself.

Proprietary Reconfigurable Flooring – A bespoke reconfigurable floor system is being installed that allows for fixtures and robots to be rapidly moved and securely and accurately fixed in place. A lack of a common or established standard in this area was noted.

For flexible, reconfigurable systems where everything is connected together and must utilise a common data format, selecting the correct data format and a common structure for its use is key. B2MML worked very well for this application, but there is still scope for variation in the way terms and variables are defined, which must be settled on.

Converting an agreed process plan for manufacturing into the B2MML has some degree of automation, but also required a large amount of manual processing. More time should have been spent on automating this process.
Ideally, all components of the system would communicate directly with the service bus. Practically, not all devices will support the service bus, so use of an intermediary communication protocol such as OPC UA may be necessary. 

Although process control may all be centralised with a manufacturing service bus, safety systems may not be. This can cause unexpected system behaviour when the system starts a new process unless the safety system is fully understood by the users. 

Selection of flexible technologies and standards does not necessarily mean that any given implementation using those technologies will be flexible. A system implementation must be designed specifically to be flexible and future proof.

The ARC robotic control system is extremely effective for bringing a robot / part to a specific and highly accurate location. However, it does not allow for accuracy along a path, so would not be appropriate for continuous path accuracy e.g. robotic milling or welding.

The large amount of metal in the cell (robots, parts) dramatically lowered the accuracy that was possible with the RFID positioning system. Rather than being able to track parts to a specific location, we could determine no better than if a part was inside or outside the cell. Active RFID tags may help mitigate this.

K-CMM technology was extremely effective, but subject to line-of-sight restrictions for large assemblies such as aerospace fuselages.

When integrating technologies and solutions from multiple equipment vendors, the challenge is almost always interoperability and standards compliance. The ARC system was comparatively simple to integrate and commission, but integration into the larger context of a manufacturing process with a SCADA and other physical devices was more of a challenge.

The experiment setup was well prepared and discussed by the experiment partners LCM and Hanning. The implementation of the solution in the CloudiFacturing Marketplace, however, was unclear and needed significant efforts during the early stages of the experiment. This partly concerned the technical solution and partly was felt in the definition and in conveying the experiment structure to the consortium.

While this has added some unplanned efforts to the experiment which then reduced the time available for the practical implementations, the cause seems quite unavoidable for wave 1 of the experiments since the development of the Marketplace happened in parallel to the experiments. This situation will, therefore, automatically improve for the experiments in wave 2.

The combined use of a simulation solution based on a numerical model and of remote HPC resources has allowed the development of a new design and development process of catamaran hulls.

The solution, which relies on Cloudifacturing platform, gives two kinds of advantages. Technically, more efficient and less defect-prone processes can be conceived and analyzed before their adoption. From an economic point of view, SME can afford the use of HPC resources without heavy investments.

"Thanks to the CloudiFacturing technology we can now take a look inside the VARTM process and switch our manufacturing process to a more safe, reliable and cheaper one", Gabriele Totisco, Catmarine CEO.