Das, M.Mohan, B.R.Ram Mohana Reddy, G.Chhaparwal, E.Krishna Kumar, K.Chowdhury, S.Sharma, S.2026-02-0620242024 IEEE Silchar Subsection Conference, SILCON 2024, 2024, Vol., , p. -https://doi.org/10.1109/SILCON63976.2024.10910879https://idr.nitk.ac.in/handle/123456789/29203Ensuring the reliability of software components is of paramount importance in safety-critical systems. Grave consequences might occur if software failures in such systems. Hence, predicting software reliability is important in these systems. This research uses Bayesian Belief Network(BBN) and leverages historical failure data to find fault interdependencies, giving much more insights than methodologies like Fault Tree Analysis (FTA) and Reliability Block Diagrams (RBD). By comparing BBNs with these traditional methods, the research shows the dynamic capabilities of BBNs. BBN also shows the capability of using real-time data and machine learning together to increase the software reliability of the software components, making this system much safer. © 2024 IEEE.Bayesian Belief NetworkConditional Probability Table (CPT)Failure rateFault Tree AnalysisOpen MarkovReliability Block Diagramsoftware reliability