Objective 1

Create data-driven process models to leverage the data generated from the physical and virtual world (Analytics) on AM machines.

Challenges DATA MANAGEMENT: Massive amounts of new online data provide significantly more raw material for data analysis. However, this data comes from diverse sources with no common schema and is of variable quality. We need radically new data management techniques to tame these huge, heterogeneous, and highly imperfect datasets. SCALABLE ALGORITHMS: The great diversity of data sources will enable a far greater range of queries than those supported by traditional data analysis systems, and the ever-increasing size of the datasets means that traditional data-analytics algorithms will require more computational resources and incur higher delays. We thus need far more flexible and scalable analysis algorithms so that, over a wide range of queries, explicit tradeoffs can be made between delay, cost, and quality of the answer.	Research Opportunities Development of scalable algorithms for analytics of manufacturing data. Prediction model for machine build failure analysis Data analysis in the supply chain for selection of suppliers.
Objectives To create a platform for asset monitoring of machine tools and provide failure analysis for predictive maintenance purposes. To create a platform for part failure analysis. Product failure root cause analysis during warranty analysis for integrated product design and quality improvement.	Equipment / Software Cloud-based Hadoop cluster subscriptions  Data Historian software
Collaborators:	Pyonyong University (Korea), VIT University

 

Objective 2

Build collaborative interfaces among smart manufacturing assets using cloud manufacturing

Challenges Using the Cloud to tackle the overhead involved in even the simplest of manufacturing tasks Addressing the issue of loss incurred due to insufficient utilization of manufacturing resources Securing the Cloud to minimize any scope of any IPR infringement Coming up with efficient algorithms that ensure optimum cost minimization and resource utilization for subscriber and the manufacturer respectively	Research Opportunities Exploring different cloud-based architectures that enable complete implementation from design to manufacturing Indigenous manufacturing-related applications development using open source and proprietary tools that are deployable on cloud Developing a highly responsive system with rapid provisioning and de-provisioning of manufacturing services Exploring the potential of hybrid cloud platforms like fog or edge computing specifically for a manufacturing environment
Objectives Define the vision, conceptual framework, reference architecture, and service models for cloud manufacturing Create models and simulation methodologies for the manufacturing cloud as a complex networked service system Build cloud manufacturing-specific data mining, processing, and optimization methods and algorithms Prototype selected instances of the reference architecture, integrating the developed models and methodologies Generate scenarios and prototype demonstrators for evaluation and validation of the developed models.	Equipment / Software Smart Factory testbed  Workstations  Cloud server and application subscriptions
Collaborators:	Prof. Xun Xu, University of Auckland,  Orzato Pvt Ltd.