Procedural Knowledge (PK) is knowing-how to perform tasks and as such is a quintessential component for industry workers in virtually all industrial fields. The challenge in PK management is that this kind of knowledge may be hard to explain and describe, oftentimes it is poorly digitalised, and, even when documented, it may be still difficult to access and retrieve.
The Horizon Europe PERKS project supports the holistic governance of industrial PK in its entire life cycle, from elicitation to management and from access to exploitation. PERKS bases its solutions on leading-edge AI (both symbolic and subsymbolic) and data technologies, by advancing and integrating existing methodologies and tools in terms of readiness, flexibility and user acceptance. Besides AI and data, the third pillar of PERKS consists of people: the goal is to put industry workers at the centre, in line with the Industry 5.0 vision, to satisfy their concrete needs, to provide AI-powered digital tools to perform their tasks better and more easily, following a human-in-the-loop paradigm to enhance the technologies and the solutions.
The results are applied in three industrial scenarios (white goods production plant: safety procedures during maintenance; CNC machines: industrial system configurability; microgrid testbed: energy consumption optimisation) providing different use cases in terms of requirements and PK complexity, enabling the measurement of industrial KPIs, and assessing PERKS’ impact on both operations and business.
PERKS leads to several innovative and exploitable outputs: a reference architecture for PK management; a set of modular, interoperable and complementary digital tools to be composed and customised to industrial requirements; specific integrated solutions to solve the challenges of the project use cases; a set of methodologies and best practices for broader application in other industrial settings, paving the way for a wider transferability of PK across contexts and sectors.
Keywords: Procedural knowledge; knowledge automation; AI; data; knowledge graphs; data spaces; user adoption; industry 5.0; safety procedures; configuration procedures; energy optimisation procedures