| CPC G06F 11/28 (2013.01) [G06N 20/00 (2019.01)] | 20 Claims |
|
1. An apparatus for analysis of preservation requirements using a dual-predictor architecture, wherein the apparatus comprises:
at least a processor, and a memory communicatively connected to the at least a processor, the memory containing instructions configuring the at least a processor to:
receive a sustainment profile, wherein the sustainment profile comprises one or more images;
identify at least a preservation need as a function of a deterioration predictor, wherein the deterioration predictor comprises a machine-learning model configured to receive the sustainment profile as an input and output a plurality of rates corresponding to a plurality of physical process variables, wherein the machine-learning model is trained using deterioration training data including a plurality of sustainment profiles inputs correlated to a plurality of rates outputs;
receive user feedback relating to the plurality of rates outputs from the machine-learning model;
determine an accuracy score for the machine-learning model based on the user feedback, wherein the accuracy score indicates to a number of retraining cycles required for the machine-learning model;
modify the deterioration training data based on the user feedback and the accuracy score to generate modified deterioration training data;
perform event-based retraining of the machine-learning model using the modified deterioration training data based on the accuracy score, wherein retraining comprises performing a convergence test requiring a predetermined mean squared error;
determine at least a relative advantage of a maintenance program as a function of an advantage predictor, wherein the advantage predictor is configured to receive the preservation need as input and output the maintenance program and the relative advantage;
display, through a graphical user interface, the at least a preservation need and relative advantage.
|