手法を比較

	フォールトツリー解析 (FTA)	ベイジアンネットワーク	イベントツリー解析 (ETA)
分野	信頼性	ベイズ	信頼性
系統	Process / pipeline	Bayesian methods	Process / pipeline
提唱年	1981	1988	2002
提唱者	Vesely et al. (US NRC Fault Tree Handbook)	Judea Pearl	Andrews & Moss
種類	Deductive top-down failure analysis	Probabilistic graphical model	Forward inductive logic tree
原典	Vesely, W. E., Goldberg, F. F., Roberts, N. H., & Haasl, D. F. (1981). Fault Tree Handbook (NUREG-0492). U.S. Nuclear Regulatory Commission.	Pearl, J. (1988). Probabilistic Reasoning in Intelligent Systems: Networks of Plausible Inference. Morgan Kaufmann. ISBN: 978-1558604797	Andrews, J. D., & Moss, T. R. (2002). Reliability and Risk Assessment (2nd ed.). Professional Engineering Publishing. ISBN: 978-1-86058-290-5
別名	FTA, Fault Tree Method, Top-Down Reliability Analysis, Hata Ağacı Analizi	Bayes network, belief network, probabilistic graphical model, directed graphical model	ETA, Event Sequence Diagram Analysis, Initiating Event Analysis, Olay Ağacı Analizi
関連	3	4	2
概要	Fault Tree Analysis (FTA) is a top-down, deductive reliability method that begins with an undesired top-level failure event and systematically traces backward through chains of contributing causes using Boolean logic gates (AND, OR). First formalized by Watson at Bell Telephone Laboratories in 1961 and later standardized by Vesely, Goldberg, Roberts, and Haasl in the landmark 1981 NRC Fault Tree Handbook, FTA has become a cornerstone of quantitative risk assessment in nuclear, aerospace, and industrial safety engineering.	A Bayesian network is a probabilistic graphical model, introduced by Judea Pearl in 1988, that encodes a set of variables and their conditional dependencies as a directed acyclic graph (DAG). Each node represents a variable; each directed edge encodes a direct probabilistic influence. By combining Bayes' rule with the graph's conditional independence structure, the model supports reasoning under uncertainty — computing the probability of any variable given observed evidence about others.	Event Tree Analysis (ETA) is a forward inductive technique used in reliability and risk engineering to model the possible outcomes that follow an initiating event. Starting from a single undesired event, ETA traces all subsequent event sequences through a binary branching tree representing the success or failure of safety barriers and protective systems. Introduced formally in reliability and risk literature by Andrews and Moss (2002), it is widely applied in nuclear, chemical, and aerospace industries to quantify accident sequence probabilities and guide safety decision-making.