Driving engineering decisions through digital transformation
A technology platform to aid engineers across design and operations that helps make informed, real-time decisions.
Research and Innovation
TCS Research
TCS Research: Inventing to build sustainable futures
In this article
Overview
The successful realization of Engineering 4.0 needs the creation of a digital thread with digital twins and contextual knowledge that drives engineering decisions across product design, manufacturing and process operations, and in-service in an integrated fashion. This would require a knowledge-guided engineering analysis with automation and integration of various steps using physics-based simulations, machine learning over data, and formal decision-support tools.
TCS Research is working on building a technology platform that can aid engineers across design and operations in making informed decisions in real time. These decisions are backed by the contextual delivery of knowledge from a digitally curated knowledge base supported by automation across complex tools and data. The technology platform being developed has been tested in diverse environments with considerable benefits and is continuously being enhanced with further research.
A technology framework to help engineers make better decisions on design and operations
Technology Description
The technology stack is developed based on a model-driven engineering framework which allows for formal specification of various entities through appropriate metamodels. This provides the flexibility to define various things at a higher level of abstraction and convert them to executable entities. Our metamodels, carefully developed for the engineering domain involving products, materials, manufacturing processes, and so on, provide a means to define subject-specific ontology. This ontology serves as ‘a semantic language’ for the expression of knowledge and data that helps achieve seamless integration between different elements of design and decision processes as shown in the image. A knowledge model allows for digital curation of knowledge in a machine-interpretable fashion on which in-silico contextual reasoning can be carried out. A process engine is guided by this knowledge to interact with the user and execute relevant tools with data in a seamless decision framework. Finally, past decisions made by the engineers is captured for further development of the knowledge base.
An engineering framework to seamlessly integrate elements in design and decision processes
Select Applications
Machine interpretable digitalization of design handbook knowledge, enabling automated verification of structural elements of an aircraft
Benefit: Accelerate the product design process
Multi-scale simulation tools are integrated to aid design across product performance and manufacturing processes.
Benefit: Make complex simulation based analysis available to designers
A new paradigm for online FMEA or RCA with actionable knowledge curated from multiple documented sources
Benefit: Advise operators on process risk and safety with reduced cognitive load
A set of multi-scale simulation tools with digitally interpretable domain knowledge to decide on process setting in production of steel sheets
Benefit: Enable field engineers to take decisions for variant product development thereby saving significant time
Potential Benefits
How the technology platform can help
