Download all project materials
Title | Abstract | |
---|---|---|
Access to Data on the Body Size and Shape of Target User Populations | Dr. Matthew Parkinson The objective of this work is to improve the performance (e.g., safety, comfort, fit) of the products, tasks, and environments with which we interact. In most cases, people are the largest source of variability in the designs they use. As a result, good practice requires data on the body size and shape of the target user populations. Unfortunately, these data are generally unavailable, expensive, or outdated. The problem is exacerbated by the rapid changes due to improved nutrition and the increased prevalence of obesity. Through support from the National Science Foundation, the OPEN Design Lab has created new methods for estimating the body size and shape of user populations. This project will use these methods to provide new tools targeting domestic and international populations. In addition to the US, the BRICS nations (Brazil, Russia, India, China, South Africa) will be targeted. Detailed anthropometry for these populations will be estimated using existing and to-be-developed methods. As a result of this effort, designers and engineers will be able to specify information about the customer population and usage scenarios and obtain detailed anthropometry (body measures) for that population. These can then be readily integrated into existing company practice. | |
Advancing Immersive Virtual Design Team Collaborations through Machine Learning | Dr. Conrad Tucker The objective of this project is to investigate the impact that immersive virtual reality environments have on design team collaborations. Engineering Design is a multidisciplinary process often involving individuals working in different geographical locations. While technologies exist that aim to bridge this gap (e.g., video conferencing), they often lack the immersive and interactive aspects of design that are critical to the success of design teams. This project will employ machine learning techniques to accurately represent designers’ actions in an immersive virtual reality environment, towards the iterative process of virtual prototype creation and evaluation. | |
Cloud-based Machine Health Monitoring and Prognosis | Dr. Dazhong Wu, Dr. Janis Terpenny, Connor Jennings The objective of the project is to develop a low cost, scalable, and data-driven intelligent process monitoring system that is capable of collecting and analyzing large-volume, high-speed heterogeneous streaming data for fault detection and prognosis in a distributed environment. The prototype will integrate cloud computing, sensor networks, parallel machine learning algorithms, and the MTConnect standard. If successful, the cloud-based machine health monitoring and prognostic system will transform the manufacturing industry by combining real-time stream processing, big data analytics, and high performance cloud computing infrastructures. | |
Cloud-Based Process Planning for CNC Code Generation | Dr. Sanjay Joshi, Dr. Dan Finke NC code generation requires non-recurring engineering time to develop process plans. Reducing this time reduces the cost of small lot production products. The objective of this project is to develop a cloud-based process planning system for CNC code generation that further extends the DARPA AVM tools. | |
Creation of Multi-Functional Structures via Embedding in Additive Manufacturing | Dr. Nick Meisel, Dr. Sven Bilen
| |
Democratizing Industrial Design Activities: A Design Team Paradigm Shift | Dr. Matthew Parkinson, Dr. Dan Finke Democratization of design activities has the potential to improve overall design, but industry does not have a way to implement. Designers are assigned tasks along functional or system boundaries and are evaluated based on how efficiently they complete their work. In a design democratization environment, assignments are more unstructured, yet the designs must be completed. This project will attempt to determine the appropriate performance metrics and processes to maximize creativity while maintaining the level of efficiency needed in an industrial setting. | |
Image-guided Additive Manufacturing | Dr. Hui Yang, Dr. Ted Reutzel The objective of this project is to design and develop an in-situ image sensing, fusion and decision-support system for real-time defect mitigation in additive manufacturing. Large amount of imaging data pose challenges on the extraction of pertinent knowledge about process dynamics for optimal control of additive manufacturing. The proposed framework of image-guided additive manufacturing will help address defects, improve build quality, and increase yield. | |
Map Reduce for Optimizing the Large-Scale Industrial Internet of Things towards Digital Manufacturing | Dr. Soundar Kumara, Dr. Hui Yang, Dr. Dan Finke The objective of this project is to develop parallel and distributed algorithms to leverage big data in the large-scale IIOT for data-driven modeling and optimization of the network of manufacturing systems. The IIOT infrastructure is not available until recently. Large-scale network of machines and data heterogeneity pose significant challenges on information processing. Efficient information processing in large-scale IIOT will help real-time decision making in manufacturing processes | |
Design Requirements Gathering using Obsolescence Forecasting | Connor Jennings, Dr. Dazhong Wu, Dr. Janis Terpenny The objective of this project is to develop a more accurate obsolescence forecasting framework using data from past products in the marketplace to predict future trends in design and the risk of component obsolescence. The framework utilizes machine learning to classify parts as actively in production or discontinued. The integration of this information into business decisions would have cost reduction effects in product design and part procurement over a product’s lifetime. | |
Product Family and Modularity: New Options through Additive Manufacturing | Dr. Tim Simpson
|