Dazhong Wu

Towards a Cloud-Based Design and Manufacturing Paradigm: Looking Backward, Looking Forward

The rise of cloud computing is radically changing the way enterprises manage their information technology (IT) assets. Considering the benefits of cloud computing to the information technology sector, we present a review of current research initiatives and applications of the cloud computing paradigm related to product design and manufacturing. In particular, we focus on exploring the potential of utilizing cloud computing for selected aspects of collaborative design, distributed manufacturing, collective innovation, data mining, semantic web technology, and virtualization. In addition, we propose to expand the paradigm of cloud computing to the field of computer-aided design and manufacturing and propose a new concept of cloud-based design and manufacturing (CBDM). Specifically, we (1) propose a comprehensive definition of CBDM; (2) discuss its key characteristics; (3) relate current research in design and manufacture to CBDM; and (4) identify key research issues and future trends.© 2012 ASME

Enhancing the Product Realization Process With Cloud-Based Design and Manufacturing Systems

The rise of cloud computing is radically changing the way enterprises manage their information technology assets. Considering the benefits of cloud computing to the information technology sector, we present a review of current research initiatives and applications of the cloud computing paradigm related to product design and manufacturing. In particular, we focus on exploring the potential of utilizing cloud computing for selected aspects of collaborative design, distributed manufacturing, collective innovation, data mining, semantic web technology, and virtualization. In addition, we propose to expand the paradigm of cloud computing to the field of computer-aided design (CAD) and manufacturing and propose a new concept of cloud-based design and manufacturing (CBDM). Specifically, we (1) propose a comprehensive definition of CBDM; (2) discuss its key characteristics; (3) relate current research in design and manufacture to CBDM; and (4) identify key research issues and future trends.

Cloud Manufacturing: Drivers, Current Status, and Future Trends

Cloud Manufacturing (CM) refers to a customer-centric manufacturing model that exploits on-demand access to a shared collection of diversified and distributed manufacturing resources to form temporary, reconfigurable production lines which enhance efficiency, reduce product lifecycle costs, and allow for optimal resource loading in response to variable-demand customer generated tasking. Our objective is to present the drivers, current status of research and development, and future trends of CM. We also discuss the potential short term and long term impacts of CM on various sectors.Copyright

A Comparative Study on Machine Learning Algorithms for Smart Manufacturing: Tool Wear Prediction Using Random Forests

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 closedform 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. [DOI: 10.1115/1.4036350]

Cloud-Based Design and Manufacturing: Status and Promise

The information technology industry has benefited considerably from cloud computing, which allows organizations to shed some of their expensive information technology infrastructure and shifts computing costs to more manageable operational expenses. In light of these benefits, we propose a new paradigm for product design and manufacturing, referred to as cloud-based design and manufacturing (CBDM). This chapter introduces a definition and vision for CBDM, articulates the differences and similarities between CBDM and traditional paradigms such as web- and agent-based technologies, highlights the fundamentals of CBDM, and presents a prototype system, developed at Georgia Tech, called the Design and Manufacturing Cloud (DMCloud). Finally, we conclude this chapter with an outline of future research directions.

Scalability Planning for Cloud-Based Manufacturing Systems

Cloud-based manufacturing (CBM) has recently been proposed as an emerging manufacturing paradigm that may potentially change the way manufacturing services are provided and accessed. In the context of CBM, companies may opt to crowdsource part of their manufacturing tasks that are beyond their existing in-house manufacturing capacity to third-party CBM service providers by renting their manufacturing equipment instead of purchasing additional machines. To plan manufacturing scalability for CBM systems, it is crucial to identify potential manufacturing bottlenecks where the entire manufacturing system capacity is limited. Because of the complexity of manufacturing resource sharing behaviors, it is challenging to model and analyze the material flow of CBM systems in which sequential, concurrent, conflicting, cyclic, and mutually exclusive manufacturing processes typically occur. To address and further study this issue, we develop a stochastic Petri nets (SPNs) model to formally represent a CBM system, model and analyze the uncertainties in the complex material flow of the CBM system, evaluate manufacturing performance, and plan manufacturing scalability. We validate this approach by means of a delivery drone example that is used to demonstrate how manufacturers can indeed achieve rapid and cost-effective manufacturing scalability in practice by combining inhouse manufacturing and crowdsourcing in a CBM setting.

SysML-based design chain information modeling for variety management in production reconfiguration

Satisfying diverse customer needs leads to proliferation of product variants. It is imperative to model the coherence of functional, product and process varieties throughout the design chain. Based on a model-based systems engineering approach, this paper applies the Systems Modeling Language (SysML) to model design chain information. To support variety management decisions, the SysML-based information models are further implemented as a variety coding information system. A case study of switchgear enclosure production reconfiguration system demonstrates that SysML-based information modeling excels in conducting requirements, structural, behavioral and constraints analysis and in performing trade-off study. In addition, it maintains semantic coherence along the design chain, keeps traceability across different levels of abstraction, thus improving interoperability among heterogeneous tools.

Understanding Communication and Collaboration in Social Product Development Through Social Network Analysis

Social media have recently been introduced into the arena of collaborative design as a new means for seamlessly gathering, processing, and sharing product design-related information. As engineering design processes are becoming increasingly distributed and collaborative, it is crucial to understand the communication and collaboration mechanism of engineers participating in such dispersed engineering processes. In particular, mapping initially disconnected design individuals and teams into an explicit social network is challenging. The objective of this paper is to propose a generic framework for investigating communication and collaboration mechanisms in social media-supported engineering design environments. Specifically, we propose an approach for measuring tie strengths in the context of distributed and collaborative design. We transform an implicit design network into an explicit and formal social network based on specific indices of tie strengths. We visualize the process of transforming customer needs to functional requirements, to design parameters, and to process variables using social network analysis (SNA). Specifically, by utilizing a specific index for tie strengths, we can quantitatively measure tie strengths in a design network. Based on the tie strengths, we can map an implicit design network into an explicit social network. Further, using the typical measures (e.g., centrality and cluster coefficient) in SNA, we can analyze the social network at both actor and systems levels and detect design communities with common design interests. We demonstrate the applicability of the framework by means of two examples. The contribution in this paper is a systematic and formal approach that helps gain new insights into communication and collaboration mechanisms in distributed and collaborative design.

Economic Benefit Analysis of Cloud-Based Design, Engineering Analysis, and Manufacturing

From a business perspective, cloud computing has revolutionized the information and communication technology (ICT) industry by offering scalable and on-demand ICT services as well as innovative pricing plans such as pay-per-use and subscription. Considering the economic benefits of cloud computing, cloud-based design and manufacturing (CBDM) has been proposed as a new paradigm in digital manufacturing and design innovation. Although CBDM has the potential to reduce costs associated with high performance computing (HPC) and maintaining ICT infrastructures in the context of cloud computing, it is challenging to justify the potential cost savings associated with design and manufacturing because of the complexity in the economic benefit analysis of migrating to CBDM. In response, this paper provides important insights into the economics of CBDM by identifying key cost factors and potential pricing models that can influence decision making on whether migrating to the cloud for computationally expensive analyses that are commonplace for design and manufacturing (e.g., computer-aided design (CAD)/computer-aided engineering (CAE)/computer-aided manufacturing (CAM)) is economically justifiable. This work, for the first time, identifies the key economic benefits required for a comparative study that supports organizations in determining when traditional in-house design and manufacturing versus CBDM is most appropriate. Several comparative case studies and a hypothetical application example are provided to demonstrate and quantitatively validate decision support methods. Finally, key issues and road blocks for CBDM are outlined.

Modeling and Analyzing the Material Flow of Crowdsourcing Processes in Cloud-based Manufacturing Systems using Stochastic Petri Nets

Cloud-based manufacturing (CBM), also referred to as cloud manufacturing, has the potential to allow manufacturing enterprises to be rapidly scaled up and down by crowdsourcing manufacturing tasks or sub-tasks. To improve the efficiency of the crowdsourcing process, the material flow of CBM systems needs to be managed so that several manufacturing processes can be executed simultaneously. Further, the scalability of manufacturing capacity in CBM needs to be designed, analyzed, and planned in response to rapidly changing market demands. The objective of this paper is to introduce a stochastic petri nets (SPNs)-based approach for modeling and analyzing the concurrency and synchronization of the material flow in CBM systems. The proposed approach is validated through a case study of a car suspension module. Our results have shown that the SPN-based approach helps analyze the structural and behavioral properties of a CBM system and verify manufacturing performance.Copyright