Machine Learning-Based Predictive Analytics for Aircraft Engine
DOI:
https://doi.org/10.17762/msea.v71i2.1935Abstract
The global business environment is being transformed by big data and artificial intelligence/machine learning. The most valuable asset for businesses in every sector is now data. To gain a competitive advantage, businesses are utilizing insights based on data. As a result, autonomous systems that support human decision-making are being developed as a result of the rapid adoption of machine learning-based data analytics across a variety of industries. The use of machine learning in the conceptual design of aircraft engines was the subject of this study. Predictive analytics that can be used to predict the performance of new turbofan designs were developed by applying supervised machine-learning algorithms for regression and classification to the patterns found in an open-source database of production and research turbofan engines. Specifically, using engine design parameters as input, the author developed machine learning-based analytics to predict cruise thrust specific fuel consumption (TSFC) and core sizes of high-efficiency turbofan engines. Keras, an open-source neural networks application program interface (API) written in Python, was used to train and deploy the predictive analytics. Google's TensorFlow, an open-source library for numerical computation, served as the backend engine. Predictive analytics' promising outcomes demonstrate the value of further research into machine learning methods for aircraft engine conceptual design