2.1 Introduction............................... 42 2.2 FaultTreeAnalysis........................... 43 2.3 Multi-Objective Evolutionary Algorithms . . . . . . . . . . . . . . 44 2.3.1 Elitist Non-dominated Sorting Genetic Algorithms . . . . . 44 2.3.2 Crowding-Distance....................... 45 2.4 Methodology .............................. 46 2.5 Thefailuredataset ........................... 46 2.6 Inferring Fault Trees via Multi-Objective Evolutionary Algorithms (FT-MOEA) ................................ 47 2.6.1 Step1-Initialisation. . . . . . . . . . . . . . . . . . . . . . 47 2.6.2 Step 1.2 - Extraction of MCSs from the failure dataset (optionalstep) ........................... 48 2.6.3 Step2-ParentFaultTrees . . . . . . . . . . . . . . . . . . 49 2.6.4 Step3-Geneticoperators. . . . . . . . . . . . . . . . . . . 49 2.6.5 Step 4 - Multi-objective function . . . . . . . . . . . . . . . 50 2.6.6 Step 5 - Convergence criteria . . . . . . . . . . . . . . . . . 51 2.7 Experimentalevaluation........................ 51 2.7.1 TheMonteCarlomethod . . . . . . . . . . . . . . . . . . . 51 2.7.2 Casestudies........................... 52 2.7.3 Key findings of the FT-MOEA algorithm............ 52 2.7.4 Parametricanalysis ...................... 55 2.8 Discussionandconclusions. . . . . . . . . . . . . . . . . . . . . . . 57 2.9 References................................ 58 3 Data-Driven Inference of Fault Tree Models Exploiting Symmetry and Modularisation 61 Abstract................................. 61 3.1 Introduction............................... 61 3.2 Modulesandsymmetries........................ 63 3.2.1 Modules............................. 63 3.2.2 Symmetries ........................... 64 3.3 Exploiting modules and symmetries in Fault Tree inference . . . . 65 3.4 Experimentalevaluation........................ 69 3.5 Conclusions ............................... 72 3.6 References................................ 73 4 Fault Tree inference using Multi-Objective Evolutionary Algorithms and Confusion Matrix-based metrics 75 Abstract................................. 75 4.1 Introduction............................... 76 4.2 Confusion Matrix-based metrics . . . . . . . . . . . . . . . . . . . . 77 4.3 FT-MOEA-CM’smethodology ...................... 78 4.4 Experimentalevaluation........................ 79 4.5 Results.................................. 80
RkJQdWJsaXNoZXIy MjY0ODMw