Differential Evolution for Optimal Grouping of Condition Monitoring Signals of Nuclear Components

We propose an approach for optimally grouping a large number of signals measured, for utilization in models for equipment condition monitoring. We use a Differential Evolution (DE) algorithm for the optimal identification 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 DE search engine functions as 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 nuclear Pressurized Water Reactor (PWR). The results of the grouping are evaluated with respect to the accuracy and robustness of the estimates of the monitored signals by the condition monitoring model developed on the optimal groups, and compared with those achieved with groups obtained using Genetic Algorithm wrapper approach.