The technological evolution emerges a unified (Industrial) Internet of Things network, where loosely coupled smart manufacturing devices build smart manufacturing systems and enable comprehensive collaboration possibilities that increase the dynamic and volatility of their ecosystems. On the one hand, this evolution generates a huge field for exploitation, but on the other hand also increases complexity including new challenges and requirements demanding for new approaches in several issues. One challenge is the analysis of such systems that generate huge amounts of (continuously generated) data, potentially containing valuable information useful for several use cases, such as knowledge generation, key performance indicator (KPI) optimization, diagnosis, predication, feedback to design or decision support. This work presents a review of Big Data analysis in smart manufacturing systems. It includes the status quo in research, innovation and development, next challenges, and a comprehensive list of potential use cases and exploitation possibilities.

No abstract

No abstract

Intelligent products, having cyber physical features, are best candidates for building Intelligent Product Service Systems (IPSS), in which integrated products and services provide a higher level of intelligence. Such IPSS may actively provide feedback on their use, which in turn may support the development of new IPSS. The objective is to develop a set of tools to establish a Collaborative Network, where both human actors and products themselves can collaborate and contribute to the development of such IPSS. The tools support involvement of various stakeholders within the Collaborative Networks. Several tools, such as a tool to select sensors and intelligent features at the products, a tool to model context under which IPSS is used, as well as tools to provide feedback on the IPSS use are defined. The paper presents as well the application of the proposed concept in machine industry.

Abstract-Nowadays, (industrial) companies invest more and more in connecting with their clients and machines deployed to the clients. Mining all collected data brings up several technical challenges, but doing it means getting a lot of insight useful for improving equipments. We define two approaches in mining the data in the context of Industrial Internet, applied to one of the leading companies in shoe production lines, but easily extendible to any producer. For each approach, various machine learning algorithms are applied along with a voting system. This leads to a robust model, easy to adapt for any machine.