P. Baraldi

Genetic algorithm-based wrapper approach for grouping condition monitoring signals of nuclear power plant components

Equipment condition monitoring of nuclear power plants requires to optimally group the usually very large number of signals and to develop for each identified group a separate condition monitoring model. In this paper we propose an approach to optimally group the signals. We use a Genetic Algorithm (GA) for the optimization of the groups; the decision variables of the optimization problem relate to the composition of the groups (i.e., which signals they contain) and the objective function (fitness) driving the search for the optimal grouping is constructed in terms of quantitative indicators of the performances of the condition monitoring models themselves: in this sense, the GA search engine is a wrapper around the condition monitoring models. A real case study is considered, concerning the condition monitoring of the Reactor Coolant Pump (RCP) of a Pressurized Water Reactor (PWR). The optimization results are evaluated with respect to the accuracy and robustness of the monitored signals estimates. The condition monitoring models built on the groups found by the proposed approach outperform the model which uses all available signals, whereas they perform similarly to the models built on groups based on signal correlation. However, these latter do not guarantee the robustness of the reconstruction in case of abnormal conditions and require to a priori fix characteristics of the groups, such as the desired minimum correlation value in a group.

Genetic algorithms for signal grouping in sensor validation: A comparison of the filter and wrapper approaches

Sensor validation is aimed at detecting anomalies in sensor operation and reconstructing the correct signals of failed sensors, e.g. by exploiting the information coming from other measured signals. In field applications, the number of signals to be monitored can often become too large to be handled by a single validation and reconstruction model. To overcome this problem, the signals can be subdivided into groups according to specific requirements and a number of validation and reconstruction models can be developed to handle the individual groups. In this paper, multi-objective genetic algorithms (MOGAs) are devised for finding groups of signals bearing the required characteristics for constructing signal validation and reconstruction models based on principal component analysis (PCA). Two approaches are considered for the MOGA search of the signal groups: the filter and wrapper approaches. The former assesses the merits of the groups only from the characteristics of their signals, whereas the latter looks for those groups optimal for building the models actually used to validate and reconstruct the signals. The two approaches are compared with respect to a real case study concerning the validation of 84 signals collected from a Swedish boiling water nuclear power plant.

Modelling the effects of maintenance on the degradation of a water-feeding turbo-pump of a nuclear power plant

This work addresses the modelling of the effects of maintenance on the degradation of an electric power plant component. This is done within a modelling framework previously proposed by the authors, of which the distinguishing feature is the characterization of the component living conditions by influencing factors (IFs), i.e. conditioning aspects of the component life that influence its degradation. The original fuzzy logic-based modelling framework includes maintenance as an IF; this requires one to jointly model its effects on the component degradation together with those of the other influencing factors. This may not come natural to the experts who are requested to provide the if-then linguistic rules at the basis of the fuzzy model linking the IFs with the component degradation state. An alternative modelling approach is proposed in this work, which does not consider maintenance as an IF that directly impacts on the degradation but as an external action that affects the state of the other IFs. By way of an example regarding the propagation of a crack in a water-feeding turbo-pump of a nuclear power plant, the approach is shown to properly model the maintenance actions based on information that can be more easily elicited from experts.

Basics of reliability and risk analysis : worked out problems and solutions

Solved Exercises on Methods for Hazard Identification Basics of Probability Theory for Applications to Reliability and Risk Analysis Reliability of Simple Systems Availability and Maintainability Fault and Event Tree Analysis Estimation of Reliability Parameters from Experimental Data Markov Chains.

On imprecision in relation to uncertainty importance measures

A number of uncertainty importance measures have been proposed in the literature to extend classical risk and reliability importance measures in the presence of epistemic uncertainty. Uncertainty impor-tance measures typically reflect to what degree uncertainty about risk and reliability parameters at the compo-nent level influences uncertainty about parameters at the system level. The definition of these measures is typically founded on a Bayesian perspective where subjective probabilities are used to express epistemic un-certainty; hence, they do not reflect the effect of imprecision in probability assignments, as captured by alter-native uncertainty representation frameworks such as imprecise probability, possibility theory and evidence theory. In the present paper we consider the issue of imprecision in relation to uncertainty importance meas-ures. We define an imprecision importance measure to evaluate the effect of removing imprecision - in the present paper focusing on imprecision removal to the extent that no epistemic uncertainty remains; as further work we suggest to also consider the more general case of imprecision removal to the extent that a probabilis-tic representation of uncertainty remains. A numerical example is presented to illustrate the suggested measure in the case of a possibilistic uncertainty representation.