Ein Bayes-Netz zur Analyse des Absturzrisikos im Gerüstbau

Oepping, Hardy (2016): Ein Bayes-Netz zur Analyse des Absturzrisikos im Gerüstbau.

Abstract

Falling from height while erecting a scaffold is one of the most prominent operative risks of a scaffolding company. Proper estimates of conditional fall probabilities considering all influencing factors are a crucial concern in assessing and implementing suitable risk control measures. This paper proposes an approach to designing a Bayesian network by which the following presumptions can be reviewed:

1. The risk of falling from height is more sensitive to length than to height of a scaffold 2. Project staff changes during running projects generally increase fall probability 3. The fall probability decreases systematically as the erecting process progresses

These presumptions will be discussed and scrutinised on the basis of a Bayesian network that provides suitable hypotheses about the relations between fall probability and its most relevant influencing factors. Theoretical implications, occurring problems, and present solutions in designing and applying the risk model will be presented in detail.

• Item Type: MPRA Paper
• English Title: A Bayesian network for analysing the risk of falling from height in scaffolding
• Language: German
• Keywords: scaffolding; falling from height; risk analysis; risk model; Bayesian network
• Subjects: C - Mathematical and Quantitative Methods > C1 - Econometric and Statistical Methods and Methodology: General > C11 - Bayesian Analysis: General; L - Industrial Organization > L7 - Industry Studies: Primary Products and Construction > L74 - Construction

References

DIN Deutsches Institut für Normung e. V. (2004), Arbeits- und Schutzgerüste - Teil 1: Schutzgerüste - Leistungsanforderungen, Entwurf, Konstruktion und Bemessung (4420-1:2004-3), Berlin: Beuth.

Druzdzel, M., Suermondt, H. (1994), "Relevance in Probabilistic Models: Backyards in a Small World", in: Working notes of the AAAI–1994 Fall Symposium Series: Relevance, 60–63.

Fenton, N. E., Neil, M. D. (2013), Risk assessment and decision analysis with Bayesian net-works, Boca Raton, Fla.: CRC Press/Chapman & Hall.

Kjærulff, U. B., Madsen, A. L. (2013), Bayesian Networks and Influence Diagrams: A Guide to Construction and Analysis, (2. Aufl.), New York: Springer.

Lin, Y., Druzdzel, M. J. (1997), "Computational Advantages of Relevance Reasoning in Bayesian Belief Networks", in: Proceedings of the Thirteenth Annual Conference on Uncertainty in Artificial Intelligence (UAI-97), 342–350.

Pearl, J. (1986), "Fusion, propagation, and structuring in belief networks", in: Artificial Intelligence 29 (3), 241–288.

Pearl, J. (1988), Probabilistic reasoning in intelligent systems. Networks of plausible infer-ence, San Mateo, Calif.: Morgan Kaufmann.

Shachter, R. D. (1986), "Evaluating Influence Diagrams", in: Operations Research 34 (6), 871–882.