Intelligent Manufacturing

Objective 1

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


  • 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.

  • 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


  • 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

  • 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.


Objective 3

Decentralize the production processes and create product architectures for distributed manufacturing


  • COST AND DIFFICULTY: The cost and difficulty of maintaining manufacturing to the same quality at several sites, of control of transport and delivery to end-user act as significant barriers.
  • SCALE-UP: A significant challenge of distributed manufacturing is the ability to up-scale whilst retaining the value that the model aims to create through personalization, localization, and inclusivity.
  • SECURITY: Challenges concerning business-to-business and business-to-consumer data sharing, governance, ownership, and security are key barriers to adoption.
  • DESIGNER CONSTRAINTS: Designers must understand the constraints of the production tools that are geographically located far away. Designers also face a risk of unpredictable financial returns, as they only earn (a percentage of the total product price) each time a design is sold online.
  • OTHER: Other Challenges include 3D modeling for AM, modular products; material supply chain issues; standards (including file formats), compatibility, regulation, and certification; the absence of software and conceptual infrastructure; the ability of organizations to create and capture value; ownership issues; and business model uncertainty
Research Opportunities

  • Development of IP policing for the prevention of copyright infringement for design and development work.
  • Development of data-sharing protocols within a digitally connected supply chain.
  • Digitalization of product design, production control, demand, and supply integration, that enable effective quality control at multiple and remote locations.
  • Investigation of products and production systems for which DM looks most promising.
  • Investigation on design rule with modularity for additive manufacturing. 

  • To develop distributed automated solutions for manufacturing and logistics
  • To develop a modular approach for the design of products to be made using DM.
  • To explore product-specific parameters based on which the safe level and nature of manufacturing distribution towards the customer end can be determined.
Equipment / Software

  • Workstations 
  • 3D CAD systems 
  • Polymer 3D printers
Collaborators: NIST USA