Applying Artifical Neural Networks To Predict Nominal Vehicle Performance

TL;DR

This study explores using artificial neural networks to automatically predict nominal vehicle performance from pre-run data, aiming to improve anomaly detection in complex, non-linear undersea vehicle test data.

Contribution

The paper demonstrates the feasibility of employing simple ANNs for vehicle performance prediction, highlighting potential advantages over traditional methods and manual review.

Findings

ANN can predict vehicle performance during transient events

ANN showed limitations in steady state and with limited training data

Potential for improved accuracy with more data and computational power

Abstract

This paper investigates the use of artificial neural networks (ANNs) to replace traditional algorithms and manual review for identifying anomalies in vehicle run data. The specific data used for this study is from undersea vehicle qualification tests. Such data is highly non-linear, therefore traditional algorithms are not adequate and manual review is time consuming. By using ANNs to predict nominal vehicle performance based solely on information available pre-run, vehicle deviation from expected performance can be automatically identified in the post-run data. Such capability is only now becoming available due to the rapid increase in understanding of ANN framework and available computing power in the past decade. The ANN trained for the purpose of this investigation is relatively simple, to keep the computing requirements within the parameters of a modern desktop PC. This ANN showed potential in predicting vehicle performance, particularly during transient events within the run data. However, there were also several performance cases, such as steady state operation and cases which did not have sufficient training data, where the ANN showed deficiencies. It is expected that as computational power becomes more readily available, ANN understanding matures, and more training data is acquired from real world tests, the performance predictions of the ANN will surpass traditional algorithms and manual human review.