An optimized back propagation neural network for automated evaluation of health condition using sensor data

Abstract

Ships and other large equipment must meet strict standards for equipment integrity and operational dependability in order to perform missions. To meet this demand, one of the essential linkages is to guarantee the long-term safe and healthy functioning of their power transmission equipment. The Optimized Back Propagation Neural Network (OBPNN) technique used in this study introduces a unique method for monitoring sensor data and evaluating the health state, with the SVM being optimized using the fish swarm algorithm (FSA). A major problem that maintenance is facing nowadays is reliable fault prediction. One of the trickiest difficulties is arguably automatically modelling typical behaviour from condition monitoring data, particularly when there is little information about actual failures. A data-driven learning framework with the best bandwidth selection is suggested to address this challenge. It is based on nonparametric density estimation for outlier identification and OBPNN for normality modelling. The distance to the separating hyper plane's log-normalization is used to provide a health score that is also available. The algorithm's viability is shown by experimental findings while evaluating the progression of a major defect over time in a marine diesel engine. Improved prediction capabilities and low false positive rates on healthy data are realized.