A Novel Framework for Qualification of a Composite-Based Main Landing Gear Strut of a Lightweight Aircraft.

The determination of suitable testing and qualification procedures for fiber-reinforced polymer matrix composite structures is an active area of research due to the increased demand, especially in the field of aerospace. This research illustrates the development of a generic qualification framework for a composite-based main landing gear strut of a lightweight aircraft. For this purpose, a landing gear strut composed of T700 carbon fiber/epoxy material was designed and analyzed for a given lightweight aircraft having mass of 1600 kg. Computational analysis was performed on ABAQUS CAE® to evaluate the maximum stresses and critical failure modes encountered during one-point landing condition as defined in the UAV Systems Airworthiness Requirements (USAR) and Air Worthiness Standards FAA FAR Part 23. A three-step qualification framework including material, process and product-based qualification was then proposed against these maximum stresses and failure modes. The proposed framework revolves around the destructive testing of specimens initially as per ASTM standards D 7264 and D 2344, followed by defining the autoclave process parameters and customized testing of thick specimens to evaluate material strength against the maximum stresses in specific failure modes of the main landing gear strut. Once the desired strength of the specimens was achieved based on material and process qualifications, qualification criteria for the main landing gear strut were proposed which would not only serve as an alternative to drop test the landing gear struts as defined in air worthiness standards during mass production, but would also give confidence to manufacturers to undertake the manufacturing of main landing gear struts using qualified material and process parameters.

Comparative analysis on Facebook post interaction using DNN, ELM and LSTM.

This study presents a novel research approach to predict user interaction for social media post using machine learning algorithms. The posts are converted to vector form using word2vec and doc2vec model. These two methods are used to analyse the best approach for generating word embeddings. The generated word embeddings of post combined with other attributes like post published time, type of post and total interactions are used to train machine learning algorithms. Deep neural network (DNN), Extreme Learning Machine (ELM) and Long Short-Term Memory (LSTM) are used to compare the prediction of total interaction for a particular post. For word2vec, the word vectors are created using both continuous bag-of-words (CBOW) and skip-gram models. Also the pre-trained word vectors provided by google is used for the analysis. For doc2vec, the word embeddings are created using both the Distributed Memory model of Paragraph Vectors (PV-DM) and Distributed Bag of Words model of Paragraph Vectors (PV-DBOW). A word embedding is also created using PV-DBOW combined with skip-gram.