DELIVERABLE D3.1 Semantically-enriched framework for analysis and design of dynamically evolving shop floor operations

DELIVERABLE D3.1 Semantically-enriched framework for analysis and design of dynamically evolving shop floor operations

The SatisFactory approach addresses multi-disciplinary technologies stemming from the deployment of a plug-and-share multi-sensorial framework for collecting effectively tacit knowledge generated in the factory environment, the delivery of a semantically enriched knowledge modelling framework (based on envisioned Common Information Data Exchange Model CIDEM) for supporting on job education of workers as well as for incident management and proactive maintenance, whereas it provides the capability to automatically verify the correctness of actions performed by the operators in the field. In this context, the deliverable D3.1 describes the semantically-enriched framework for the analysis and design of shop floor operations along with the corresponding software. This framework provides a light weight and full semantic interoperability to support User Interaction with the Context aware engine and the Decision Support System (Task 3.5). Aiming at achieving context-aware control and re-adaptation of shop floor production facilities for increased productivity and flexibility in use of shop floor resources, a novel multi-sensorial framework is introduced for collecting multi-modal data from the shop floor. The input data streams are aggregated and processed, creating a semantically enhanced base of knowledge, which can be finally utilized to extract intra-factory information concerning production facilities and procedures (machineries, processes, products, production lines, workplaces) and to monitor in real-time the evolving production processes, diagnose problems, flaws and malfunctions (e.g. problems to intermediate or final product). Collected dynamic data are combined with static data describing the production environment, in order to feed the SatisFactory novel model of workplace occupancy evolution and prediction of future needs. The model supports planning and balancing the workload density more efficiently for both the workers and the factory, in terms of balance across available workers in each shift, balance according to production demand highs/lows, etc. SatisFactory provides an application based on the above framework that is able to decide which information is relevant in a particular situation for a specific user. In order to accomplish that, an ontology-based context model which captures the general concepts about user and business context is developed. A set of rules coming from prior “hands-on” knowledge and previous experience enrich the knowledge model in order to achieve human resource optimization. The use of semantic technologies in T3.1 makes the model both human and machine understandable, addressing the issue based on the dynamically expanding and semantically enhanced knowledge database.Algorithmic tools for object and task recognition supported by augmented reality will then form the basis for employee training on-the-job without the need of the continuous attention of an educator.Based on the semantic models presented in this deliverable, the DSS will be designed in order to make a step forward towards a better understanding of the involved manufacturing processes and operations, the shop floor actors and machinery, the worker’s roles and responsibilities, the maintenance requirements and procedures and the daily production details and flaws

More information
Web resources:
Demonstration level: Level 0 - Level not specified
Attached files
No attachments available