Helicopter Turboshaft Engines’ Neural Network System for Monitoring Sensor Failures

TL;DR

A neural network system using LSTM and GRU was developed to monitor sensor failures in helicopter engines, achieving high accuracy and fast training times.

Contribution

A novel hybrid LSTM-GRU neural network system with adaptive discretization techniques for improved sensor failure monitoring in helicopter engines.

Findings

The system achieved 99.327% anomaly detection accuracy after 200 training epochs.

Training time was reduced to 4 min and 13 s using a combined SGD and RMSProp optimization method.

The system outperformed alternative methods with an accuracy of 0.993 versus 0.981 and 0.982.

Abstract

An effective neural network system for monitoring sensors in helicopter turboshaft engines has been developed based on a hybrid architecture combining LSTM and GRU. This system enables sequential data processing while ensuring high accuracy in anomaly detection. Using recurrent layers (LSTM/GRU) is critical for dependencies among data time series analysis and identification, facilitating key information retention from previous states. Modules such as SensorFailClean and SensorFailNorm implement adaptive discretization and quantisation techniques, enhancing the data input quality and contributing to more accurate predictions. The developed system demonstrated anomaly detection accuracy at 99.327% after 200 training epochs, with a reduction in loss from 2.5 to 0.5%, indicating stability in anomaly processing. A training algorithm incorporating temporal regularization and a combined optimization method (SGD with RMSProp) accelerated neural network convergence, reducing the training time to 4 min and 13 s while achieving an accuracy of 0.993. Comparisons with alternative methods indicate superior performance for the proposed approach across key metrics, including accuracy at 0.993 compared to 0.981 and 0.982. Computational experiments confirmed the presence of the highly correlated sensor and demonstrated the method’s effectiveness in fault detection, highlighting the system’s capability to minimize omissions.

Figures