Shafiq, AnumColak, Andac BaturSindhu, Tabassum Naz2024-11-072024-11-0720220748-80171099-1638https://doi.org/10.1002/qre.3155https://hdl.handle.net/11480/15439In current investigation, a novel implementation of intelligent numerical computing solver depending on artificial neural networks (ANN) has been provided to interpret failure function (FF), reliability function (RF), hazard rate function (HRF), Mils ratio (MR), and mean time to failure (MTTF). This study investigates a reliability model centered on the exponentiated Weibull distribution (EWD) and the inverse power law (IPL) model employing the ANN model. The nonmonotonic failure rate can be modeled via this distribution. A data set for the proposed ANN has been generated for various scenarios of (Exponentiated Weibull Inverse Power Law Distribution) EWIPLD model by variation of involved pertinent parameters via the Galerkin weighted residual method (GWRM). Levenberg-Marquard training algorithm has been used in the multi-layer perceptron (MLP) network model developed with 10 nodes in the hidden layer. The Coefficient of Determination (R) value for the ANN model has been obtained as 0.9999. The findings obtained, revealed that ANNs are an excellent technique that can be applied to predict reliability measures in conjunction with the right statistical model.eninfo:eu-repo/semantics/closedAccessEWIPLDartificial neural networkpower devicesfeed-forward back-propagationmean time to failureArticle3873616363110.1002/qre.31552-s2.0-85132071388Q2WOS:000812591900001Q3