Change from Machines to Production Systems—An Approach and Qualitative Methods for the Assessment of System Safety and System Availability Risks

In the modern industrial world, effective role of maintenance activities in the survival of organizations and enhancing their productivity is undeniable.Variety of equipments in the industrial organizations and their exclusivities in terms of longevity and failures modes, clear the importance of choosing a strategy for the maintenance of any equipment. Thus, knowing the type of the failure is so important for maintenance manager and engineers.Important introduced indicators in this domain such as indicator of reliability, MTBF and MTTR can be used to predicting and detecting approximate failure time and analyzing life cycle status.On the other hand, due to fluctuating time of system availability because of work continuity and loss of a performance indicator, by combining RCM indicators and Overall Equipment Effectiveness (OEE) indicator the most compatible strategy could be chosen. The aim of this article which differs from other studies in this field is to apply a composed indicator, including different parameters of RCM, which is obtained based on the equipment life status.

Download Full-text

Fault-Tolerant Control of Programmable Logic Controller-Based Production Systems With Deep Reinforcement Learning

Journal of Mechanical Design ◽

10.1115/1.4050624 ◽

2021 ◽

Vol 143 (7) ◽

Author(s):

Jonas Zinn ◽

Birgit Vogel-Heuser ◽

Marius Gruber

Keyword(s):

Reinforcement Learning ◽

Production Systems ◽

Fault Tolerant ◽

Fault Tolerant Control ◽

Fault Recovery ◽

Suggested Approach ◽

System Availability ◽

Automated Production ◽

Multi Agent ◽

End Effectors

Abstract Fault-tolerant control policies that automatically restart programable logic controller-based automated production system during fault recovery can increase system availability. This article provides a proof of concept that such policies can be synthesized with deep reinforcement learning. The authors specifically focus on systems with multiple end-effectors that are actuated in only one or two axes, commonly used for assembly and logistics tasks. Due to the large number of actuators in multi-end-effector systems and the limited possibilities to track workpieces in a single coordinate system, these systems are especially challenging to learn. This article demonstrates that a hierarchical multi-agent deep reinforcement learning approach together with a separate coordinate prediction module per agent can overcome these challenges. The evaluation of the suggested approach on the simulation of a small laboratory demonstrator shows that it is capable of restarting the system and completing open tasks as part of fault recovery.

Download Full-text

Qualitative methods in nursing planning and structure of teaching units in nursing

Pflege ◽

10.1024/1012-5302.12.1.52 ◽

1999 ◽

Vol 12 (1) ◽

pp. 52-57

Author(s):

Tilmann Netz

Keyword(s):

Qualitative Methods

Um die direkte Pflege weiter zu professionalisieren, ist es notwendig, neue Lehrmethoden für Aus- und Fortbildung zu entwickeln. Werden qualitative Verfahren bei der Planung und Gestaltung von Lehreinheiten im Fachbereich Pflege favorisiert, so werden auch subjektive Theorien transparent, die das Pflegegeschehen unterschwellig beeinflussen. Ziel handlungsorientierter Unterrichtseinheiten im Fachbereich Pflege ist, diese gezielt im Sinne des neuen Pflegeparadigmas zu beeinflussen.

Download Full-text