Browsing by Author "Han, Ji"
Now showing 1 - 2 of 2
Results Per Page
Sort Options
Item Open Access A computational approach to identifying engineering design problems(American Society of Mechanical Engineers (ASME), 2023-01-09) Obieke, Chijioke C.; Milisavljevic-Syed, Jelena; Silva, Arlindo; Han, JiIdentifying new problems and providing solutions are necessary tasks for design engineers at early-stage product design and development. A new problem fosters innovative and inventive solutions. Hence, it is expected that engineering design pedagogy and practice should equally focus on engineering design problem-exploring (EDPE)—a process of identifying or coming up with a new problem or need at the early-stage of design, and engineering design problem-solving (EDPS)—a process of developing engineering design solutions to a given problem. However, studies suggest that EDPE is scarcely practiced or given attention to in academia and industry, unlike EDPS. The aim of this paper is to investigate the EDPE process for any information relating to its scarce practice in academia and industry. This is to explore how emerging technologies could support the process. Natural models and phenomena that explain the EDPE process are investigated, including the “rational” and “garbage can” models, and associated challenges identified. A computational framework that mimics the natural EDPE process is presented. The framework is based on Markovian model and computational technologies, including machine learning. A case study is conducted with a sample size of 43 participants drawn worldwide from the engineering design community in academia and industry. The case study result shows that the first-of-its-kind computational EDPE framework presented in this paper supports both novice and experienced design engineers in EDPE.Item Open Access Predictive modeling for the quantity of recycled end-of-life products using optimized ensemble learners(Elsevier, 2023-06-09) Xia, Hanbing; Han, Ji; Milisavljevic-Syed, JelenaThe rapid development of machine learning algorithms provides new solutions for predicting the quantity of recycled end-of-life products. However, the Stacking ensemble model is less widely used in the field of predicting the quantity of recycled end-of-life products. To fill this gap, we propose a Stacking ensemble model that utilizes support vector regression, multi-layer perceptrons, and extreme gradient boosting algorithms as base models, and linear regression as the meta model. The k-nearest neighbor mega-trend diffusion method is applied to avoid overfitting problems caused by a small sample data set. The grid search and time series cross validation methods are utilized to optimize the proposed model. To verify and validate the proposed model, data related to China's end-of-life vehicles industry from 2006 to 2020 is used. The experimental results demonstrate that the proposed model achieves higher prediction accuracy and generalization ability in predicting the quantity of recycled end-of-life products.