In the frame of the project we developed and presented an evolving fuzzy method based on data clouds for fault detection and identification of dynamic processes. The method calculates the local density of the data using the recursive Mahalanobis distance through recursive calculation of the inverse of the covariance matrix. The structure of the fuzzy model evolves in an online manner and it is capable to incorporate new knowledge in the model. The method was realized for Metronik d.o.o..
F.14 Improvements to existing production methods and tools or processes
COBISS.SI-ID: 12510292Study focuses on the development of control algorithms for micro-scale navigation of AGVs, allowing the AGV to plan and execute an obstacle avoidance path around the encountered obstacle. Nominally, AGVs follow the path, defined with the magnetic tape on the driving surface, and stop in front of an obstacle if one is encountered. If allowed by the central management system of the plant, the presented system takes over the control of the AGV at that point and first plans, then executes the obstacle avoidance path. The study includes development of control algorithms, planning software and presents the results of experiments, executed both in laboratory and industrial environment.
F.13 Development of new production methods and tools or processes
COBISS.SI-ID: 12873044The invention deals with the control system design, inclusion and implementation in a smart walking assist system, that improves the existing, mostly manual controlled, walking assist system, used during the walk rehabilitation process. The invention relates to the novel approach on observing the user intentions and producing motion control signals for the platform’s drivetrain in order to allow the platform to intuitively follow the user. This is accomplished by measuring vertical strut deflections from the vertical position and processing this information as an assessment of user intention of the motion for the platform.
F.32 International patent
COBISS.SI-ID: 12811092