Search for: All records

With design teams becoming more distributed, the sharing and interpreting of complex data about design concepts/prototypes and environments have become increasingly challenging. The size and quality of data that can be captured and shared directly affects the ability of receivers of that data to collaborate and provide meaningful feedback. To mitigate these challenges, the authors of this work propose the real-time translation of physical objects into an immersive virtual reality environment using readily available red, green, blue, and depth (RGB-D) sensing systems and standard networking connections. The emergence of commercial, off-the-shelf RGB-D sensing systems, such as the Microsoft Kinect, has enabled the rapid three-dimensional (3D) reconstruction of physical environments. The authors present a method that employs 3D mesh reconstruction algorithms and real-time rendering techniques to capture physical objects in the real world and represent their 3D reconstruction in an immersive virtual reality environment with which the user can then interact. Providing these features allows distributed design teams to share and interpret complex 3D data in a natural manner. The method reduces the processing requirements of the data capture system while enabling it to be portable. The method also provides an immersive environment in which designers can view and interpret the data remotely. A case study involving a commodity RGB-D sensor and multiple computers connected through standard TCP internet connections is presented to demonstrate the viability of the proposed method. 

Manufacturers have faced an increasing need for the development of predictive models that predict mechanical failures and the remaining useful life (RUL) of manufacturing systems or components. Classical model-based or physics-based prognostics often require an in-depth physical understanding of the system of interest to develop closed-form mathematical models. However, prior knowledge of system behavior is not always available, especially for complex manufacturing systems and processes. To complement model-based prognostics, data-driven methods have been increasingly applied to machinery prognostics and maintenance management, transforming legacy manufacturing systems into smart manufacturing systems with artificial intelligence. While previous research has demonstrated the effectiveness of data-driven methods, most of these prognostic methods are based on classical machine learning techniques, such as artificial neural networks (ANNs) and support vector regression (SVR). With the rapid advancement in artificial intelligence, various machine learning algorithms have been developed and widely applied in many engineering fields. The objective of this research is to introduce a random forests (RFs)-based prognostic method for tool wear prediction as well as compare the performance of RFs with feed-forward back propagation (FFBP) ANNs and SVR. Specifically, the performance of FFBP ANNs, SVR, and RFs are compared using an experimental data collected from 315 milling tests. Experimental results have shown that RFs can generate more accurate predictions than FFBP ANNs with a single hidden layer and SVR. 

Abstract This paper (Wu 2016), which was published in AI EDAM online on August 22, 2016, has been retracted by Cambridge University Press as it is very similar in content to a published ASME Conference Proceedings paper. The article in question and the ASME Conference Proceedings paper were submitted for review with AI EDAM and the ASME at similar times, but copyright was assigned to ASME before the paper was accepted in AI EDAM and therefore the article in AI EDAM is being retracted. (In recent years, industrial nations around the globe have invested heavily in new technologies, software, and services to advance digital design and manufacturing using cyber-physical systems, data analytics, and high-performance computing. Many of these initiatives, such as cloud-based design and manufacturing, fall under the umbrella of what has become known as Industry 4.0 or Industrial Internet and are often hailed as pillars of a new industrial revolution. While an increasing number of companies are developing or already offer commercial cloud-based software packages and services for digital design and manufacturing, little work has been reported on providing a review of the state of the art of these commercial software and services as well as identifying research gaps in this field. The objective of this paper is to present a state-of-the-art review of digital design and manufacturing software and services that are currently available on the cloud. The focus of this paper is on assessing to what extent engineering design, engineering analysis, manufacturing, and production across all phases of the product development lifecycles can already be performed based on the software and services accessed through the cloud. In addition, the key capabilities and benefits of these software packages and services are discussed. Based on the assessment of the core features of commercial software and services, it can be concluded that almost all phases of product realization can be conducted through digital design and manufacturing software and services on the cloud. Finally, existing research gaps and related challenges to overcome are identified. The state-of-the-art review serves to provide a technology guide for decision makers in their efforts to select suitable cloud-based software and services as alternatives to existing in-house resources as well as to recommend new research areas.) 

With rapid innovation in the electronics industry, product obsolescence forecasting has become increasingly important. More accurate obsolescence forecasting would have cost reduction effects in product design and part procurement over a product’s lifetime. Currently many obsolescence forecasting methods require manual input or perform market analysis on a part by part basis; practices that are not feasible for large bill of materials. In response, this paper introduces an obsolescence forecasting framework that is capable of being scaled to meet industry needs while remaining highly accurate. The framework utilizes machine learning to classify parts as active, in production, or obsolete and discontinued. This classification and labeling of parts can be useful in the design stage in part selection and during inventory management with evaluating the chance that suppliers might stop production. A case study utilizing the proposed framework is presented to demonstrate and validate the improved accuracy of obsolescence risk forecasting. As shown, the framework correctly identified active and obsolete products with an accuracy as high as 98.3%.