Порівняння методів

	Симуляційно-допоміжна аналіз подійних дерев (ETA)	Байєсівський аналіз дерев подій
Галузь	Планування експерименту	Планування експерименту
Родина	Process / pipeline	Process / pipeline
Рік появи	1970s–1990s (formalized in probabilistic risk assessment practice)	ETA: 1960s–1970s; Bayesian extension: 1990s–2000s
Автор методу	H.A. Watson (Bell Telephone Laboratories, ETA origins ~1961); Monte Carlo integration of ETA developed in nuclear/aerospace PRA community 1970s–1990s	H.E. Watson (Bell Labs, fault tree); ETA formalized via US Nuclear Regulatory Commission; Bayesian extension developed in reliability and risk engineering communities
Тип	Probabilistic risk and reliability assessment method	Probabilistic risk and reliability analysis technique
Основоположне джерело	Zio, E. (2009). Reliability engineering: Old problems and new challenges. Reliability Engineering and System Safety, 94(2), 125–141.	Bearfield, G., & Marsh, W. (2005). Generalising event trees using Bayesian networks with a case study of train derailment. In G. Windeknecht et al. (Eds.), Proceedings of the 13th Safety-Critical Systems Symposium. Springer.
Інші назви	Monte Carlo ETA, stochastic event tree analysis, simulation-enhanced ETA, probabilistic event tree simulation	Bayesian ETA, B-ETA, Probabilistic Event Tree Analysis, Bayesian Inductive Risk Model
Пов'язані	6	5
Підсумок	Simulation-assisted event tree analysis (ETA) extends classical event tree analysis by replacing fixed point-estimate branch probabilities with Monte Carlo or discrete-event simulation. This allows analysts to propagate uncertainty through every branch of the tree and obtain full probability distributions over accident sequences and system outcomes, yielding far richer risk insights than deterministic ETA alone.	Bayesian Event Tree Analysis (B-ETA) is a quantitative risk assessment method that extends classical event tree analysis by incorporating Bayesian inference to assign and update branch probabilities. Starting from an initiating event, it maps sequences of successes and failures through safety barriers, using prior distributions and observed evidence to produce posterior outcome probabilities. Widely used in nuclear safety, process industries, and system reliability engineering.