Optimization of Unmanned Aerial Vehicle Flight Control Sensor Control System based on Deep Learning Model

Abstract

Based on data modelling strategies have created reliable classifier designs for various classes and other neural network applications. The fact that modelling complexity rises with the total number of groups in the system does is one of the approach's major shortcomings. No matter how well it performs, it could make the classifier's design ugly. This article discusses the development of a novel, logic-based Optimum Bayesian Gaussian process (OBGP) classifier to reduce the number of separate empirical models required to accurately detect various fault types in industrial processes. The precision of the OBGP classifier's defining faults also contrasts with the results of other approaches documented in the literature.