Quantifying Component Importance for Disaster Resilience of Communities with Interdependent Civil Infrastructure Systems

Communities and their supporting civil infrastructure systems can be viewed as an assembly of, often numerous, interacting components. Tools that can identify components relevant for community disaster resilience can help to efficiently allocate limited resources to reach community resilience goals. We use Sobol’ indices to measure the importance of vulnerability and recoverability of components for disaster resilience of communities with interdependent civil infrastructure systems. The initial component importance analysis requires no prior knowledge regarding component’s vulnerability and recoverability. We first rank components based on their importance, using their Sobol’ indices. Secondly, we illustrate how the results of the component importance analysis can be used to improve community disaster resilience. Finally, we use component importance to show how model complexity can be reduced by abstracting less important components.

Machine Learning Approaches to Determine Feature Importance for Predicting Infant Autopsy Outcome

Introduction Sudden unexpected death in infancy (SUDI) represents the commonest presentation of postneonatal death. We explored whether machine learning could be used to derive data driven insights for prediction of infant autopsy outcome. Methods A paediatric autopsy database containing >7,000 cases, with >300 variables, was analysed by examination stage and autopsy outcome classified as ‘explained (medical cause of death identified)’ or ‘unexplained’. Decision tree, random forest, and gradient boosting models were iteratively trained and evaluated. Results Data from 3,100 infant and young child (<2 years) autopsies were included. Naïve decision tree using external examination data had performance of 68% for predicting an explained death. Core data items were identified using model feature importance. The most effective model was XG Boost, with overall predictive performance of 80%, demonstrating age at death, and cardiovascular and respiratory histological findings as the most important variables associated with determining medical cause of death. Conclusion This study demonstrates feasibility of using machine-learning to evaluate component importance of complex medical procedures (paediatric autopsy) and highlights value of collecting routine clinical data according to defined standards. This approach can be applied to a range of clinical and operational healthcare scenarios

Reliability Importance Measures-Based Analysis of Substation Communication Network

Smart grid can work effectively only when a reliable, fast communication network is available. The communication network is a prerequisite to connect different protection, control, and monitoring equipment within the substation. Ethernet fulfills all the requisites such as reliable, fast, secure, interoperable, LAN-based communication system for smart substations. Therefore, the main aspect is to improve the reliability of the network by prioritizing the critical components by using the knowledge of component importance measures (CIM). In this chapter, analysis of IEC 61850 ethernet-based substation communication network (SCN) architectures has been examined using various reliability importance measures (RIM). The importance measures namely Birnbaum, improvement potential, criticality importance, and reliability achievement worth have given their justified rankings of the various components of SCN architectures. The practice of these CIMs works towards the identification of the components that can be allocation of resources for the improvement of system reliability.

Research on Time-Dependent Component Importance Measures Considering State Duration and Common Cause Failure

Unlike the current risk monitors, Real-time Online Risk Monitoring and Management Technology is characterized by time-dependent modeling on the state duration of components. Given the real-time plant configuration, it eventually provides the time-dependent risk level and importance measures for operation and maintenance management. This paper focuses on the assessment method of time-dependent importance measures and its risk-informed applications in real-time online risk monitoring and management technology, including Fussell-Vesely (FV), risk achievement worth (RAW), and risk reduction worth (RRW). In this study, the values of component importance have been investigated with a time-dependent risk quantification model, as well as the common cause failure treatment model. Here three options of common cause failure treatment have been developed, assuming that the unavailability of a component could be due to an independent factor (Option 1), a common cause factor (Option 2), or an unconfirmed cause (Option 3). In the special case of “what if a component is out-of-service” of the RAW numerator, a hybrid method for the RAW evaluation is presented resulting in a balanced and reasonable RAW value. A simple case study was demonstrated. The results showed that the absolute values and ranking order of time-dependent importance not only reflected the effect of the cumulative state duration of component on risk, but also comprehensively accounted for all possible situations of component unavailability. Moreover, time-dependent importance measures improved and provided novel insights for online configuration management, 1) ranking SSCs/events/human actions for controlling increased risk and optimizing near–term plans; and 2) exempting or limiting temporary configurations during online operation.

Identification of Power Transformer Currents by Using Random Forest and Boosting Techniques

In this research, a differential protection technique for a power transformer is proposed by using random forest and boosting learning machines. The proposed learning machines aim to provide a protection expert system that distinguishes between different transformer status which are normal, inrush, overexcitation, CT saturation, or internal fault. Data for 20 different transformers with 5 operating cases are used in this research. The utilized random forest and boosting techniques are trained using these data. Meanwhile, the proposed models are validated by other measures such as out-of-bag error and confusion matrix. In addition, variable importance analysis that shows signal’s component importance inside a transformer at different instances is provided. According to the result, the proposed random forest model successfully identifies all of the current cases (100% accuracy for the conducted experiment). Meanwhile, it is found that it is less accurate as a conditional monitoring element with accuracy in the range of 97%–98%. On the other hand, the proposed boosting model identifies all of the currents for both cases (100% accuracy for the conducted experiment). In addition to that, a comparison is conducted between the proposed models and other AI-based models. Based on this comparison, the proposed boosting model is the simplest and the most accurate model as compared to other models.

Representations of component importance for coherent systems with exchangeable components

Two definitions of Birnbaum’s importance measure for coherent systems are studied in the case of exchangeable components. Representations of these measures in terms of distribution functions of the ordered component lifetimes are given. As an example, coherent systems with failure-dependent component lifetimes based on the notion of sequential order statistics are considered. Furthermore, it is shown that the two measures are ordered in the case of associated component lifetimes. Finally, the limiting behavior of the measures with respect to time is examined.