In the recent years, automakers have been striving to improve the carbon footprint of their vehicles. Sustainable composites, consisting of natural fibers, and/or recycled polymers have been developed as a way to increase the “green content” and reduce the weight of a vehicle. In addition, recent studies have found that the introduction of synthetic fibers to a traditional fiber composite such as glass filled plastics, producing a composite with multiple fillers (hybrid fibers), can result in superior mechanical properties. The objective of this work was to investigate the effect of hybrid fibers on characterization and material properties of polyamide-6 (PA6)/polypropylene (PP) blends. Cellulose and glass fibers were used as fillers and the mechanical, water absorption, and morphological properties of composites were evaluated. The addition of hybrid fibers increased the stiffness (tensile and flexural modulus) of the composites. Glass fibers reduced composite water absorption while the addition of cellulose fibers resulted in higher composite stiffness. The mechanical properties of glass and cellulose filled PA6/PP composites were optimized at loading levels of 15 wt% glass and 10 wt% cellulose, respectively.

Predicting Remaining Useful Life (RUL) of systems has played an important role in various fields of reliability engineering analysis, including in aircraft engines. RUL prediction is critically an important part of Prognostics and Health Management (PHM), which is the reliability science that is aimed at increasing the reliability of the system and, in turn, reducing the maintenance cost. The majority of the PHM models proposed during the past few years have shown a significant increase in the amount of data-driven deployments. While more complex data-driven models are often associated with higher accuracy, there is a corresponding need to reduce model complexity. One possible way to reduce the complexity of the model is to use the features (attributes or variables) selection and dimensionality reduction methods prior to the model training process. In this work, the effectiveness of multiple filter and wrapper feature selection methods (correlation analysis, relief forward/backward selection, and others), along with Principal Component Analysis (PCA) as a dimensionality reduction method, was investigated. A basis algorithm of deep learning, Feedforward Artificial Neural Network (FFNN), was used as a benchmark modeling algorithm. All those approaches can also be applied to the prognostics of an aircraft gas turbine engines. In this paper, the aircraft gas turbine engines data from NASA Ames prognostics data repository was used to test the effectiveness of the filter and wrapper feature selection methods not only for the vanilla FFNN model but also for Deep Neural Network (DNN) model. The findings show that applying feature selection methods helps to improve overall model accuracy and significantly reduced the complexity of the models.

Thermoplastic resins (linear low-density polyethylene (LLDPE), high-density polyethylene (HDPE), and polypropylene (PP)) reinforced by different content ratios of raw agave fibers were prepared and characterized in terms of their mechanical, thermal, and chemical properties as well as their morphology. The morphological properties of agave fibers and films were characterized by scanning electron microscopy and the variations in chemical interactions between the filler and matrix materials were studied using Fourier-transform infrared spectroscopy. No significant chemical interaction between the filler and matrix was observed. Melting point and crystallinity of the composites were evaluated for the effect of agave fiber on thermal properties of the composites, and modulus and yield strength parameters were inspected for mechanical analysis. While addition of natural fillers did not affect the overall thermal properties of the composite materials, elastic modulus and yielding stress exhibited direct correlation to the filler content and increased as the fiber content was increased. The highest elastic moduli were achieved with 20 wt % agave fiber for all the three composites. The values were increased by 319.3%, 69.2%, and 57.2%, for LLDPE, HDPE, and PP, respectively. The optimum yield stresses were achieved with 20 wt % fiber for LLDPE increasing by 84.2% and with 30 wt % for both HDPE and PP, increasing by 52% and 12.3% respectively.

In most cases, plant containers used in the horticulture industry are not reusable, have many negative impacts on the environment, and take a long time to degrade. To reduce the use of non-biodegradable plant containers, many bio-degradable plant containers have been developed for the horticulture industry. However, the full potential of the sustainability of plant containers is yet to be completely explored. Therefore, two novel biodegradable plant containers are developed in this research to effectively contribute to sustainability’s environmental, social, and economic dimensions. The two biocomposite formulations are developed by mixing soy hull and soy protein isolate (SPI) with polylactic acid (PLA) matrix for plant containers. In the first formulation, the proportion of PLA and soy hulls are 70 wt% and 30 wt%, respectively; in the second formulation, 65 wt% PLA is blended with 30 wt% soy hulls and 5 wt% SPI. The injection molding process is used to manufacture the plant containers from the two formulations. In a field trial, four plant species are grown in the novel plant containers along with polyethylene and commercial PLA/DDGS (dried distiller’s grains with solubles and PLA-based container) containers to investigate biodegradability and plant growth. The results show that the containers from the new formulations outperform existing biodegradable PLA/DDGS containers in terms of certain plant growth and biodegradability.