Aviation Equipment Residual Life Determination Based on Neural Network Technologies
A multilayer perceptron training method based on the backpropagation algorithm has been developed to enhance the helicopter turboshaft engines' residual life-predicting accuracy by integrating the initial parameter into the output layer. Using the Adam optimizer for adaptive learning rates achieves high accuracy (up to 99.3%) in determining the residual life of compressor turbine blades. Experiments show that this method, with 160 epochs, reaches 99.3% accuracy and reduces losses to 0.5% in solving the residual life estimation task.
Authors
- Svitlana Sachenko (ORCID: https://orcid.org/0000-0001-8225-1820)
- Victoria Vysotska (ORCID: https://orcid.org/0000-0001-6417-3689)
- Anatoliy Sachenko (ORCID: https://orcid.org/0000-0002-0907-3682)
- Oleksandr Muzychuk (ORCID: https://orcid.org/0000-0001-8367-2504)
- Валерій Сокуренко (ORCID: https://orcid.org/0000-0001-8923-5639)
- Serhii Vladov (ORCID: https://orcid.org/0000-0001-8009-5254)
Institutions
- West Ukrainian National University (UA)
- Kharkiv National University of Internal Affairs (UA)
- Lviv Polytechnic National University (UA)
Publication Details
- Published
- 2024-10-16
- DOI
- https://doi.org/10.1109/csit65290.2024.10982601
- Primary Topic
- Engineering Diagnostics and Reliability
- Type
- article
- Field-Weighted Citation Impact
- 0.00