National Chung Cheng University · Taiwan

Deep Intelligence
Lab for X

A research community advancing Trustworthy AI, Smart Manufacturing, Robotics, and Physical AI — intelligent systems that positively impact society, industry, and the world.

“Intelligence with Purpose, Innovation with Heart.”

30+
Publications & Chapters
5
Countries Collaborating
1
NSTC Funded Project
About the Lab

A Way Towards Intelligent Manufacturing, Robotics, and Beyond

DIL-X (Deep Intelligence Lab for X) is an interdisciplinary research laboratory where Artificial Intelligence is developed not merely as a computational tool, but as a responsible, trustworthy, and human-centered technology for real-world industrial and societal challenges.

The meaning of DIL

In Hindi and Urdu, Dil means Heart — the meeting point of mind, emotion, purpose, and human aspiration. It represents embodied intelligence: the integration of cognition, ethics, creativity, and action that guides human decision-making.

The meaning of X

X represents possibility, exploration, and discovery — the unknown challenge yet to be solved, the technology yet to be invented. There is no predefined X. Every researcher discovers their own through curiosity and purpose.

Our Vision

To become a globally recognized research laboratory advancing responsible intelligence across physical, digital, and human-centered systems for the benefit of society and future generations.

Our Mission

To discover, create, and deploy intelligent systems that advance society through responsible innovation, scientific excellence, interdisciplinary collaboration, and human-centered design.

Human-Centered Innovation Responsible AI Sustainable Engineering Global Collaboration Scientific Excellence with Heart

Our Belief

The Heart inspires the Purpose · The Purpose drives Discovery · Discovery creates Impact.
The X is yours — discover it, research it, build it, use it responsibly.

Principal Investigator

Meet the Principal Investigator

Dr. Ayush Pratap is the Founder and Principal Investigator of DIL-X (Deep Intelligence Lab for X) and an Assistant Professor in the Department of Mechanical Engineering at National Chung Cheng University (CCU), Taiwan. He previously served as an Assistant Researcher at the Advanced Institute of Manufacturing with High-tech Innovations (AIM-HI), CCU.

He earned a Joint Ph.D. from the Indian Institute of Technology (IIT) Ropar, India (Metallurgical & Materials Engineering) and CCU, Taiwan (Ambient Intelligence and Smart Systems) — as the first graduate of this interdisciplinary international joint doctoral program.

His research lies at the intersection of Trustworthy AI, Smart Manufacturing, Robotics, Physical AI, Digital Twins, Physics-Informed Machine Learning, Large Language Models, Foundation Models, and Agentic AI. As Principal Investigator, he leads the NSTC-funded project “PINN-FM: Development of a Physics-Informed Neural Network-Based Foundation Model for Machining Industry Orchestration” (from August 2026).

He is also the founder of OptiMOS.AI, an AI-assisted semiconductor design startup incubated at Startup Land, CCU, and a published Hindi poet (“Dil-e-nazm Part 1”).

Education

2020–2025
Joint Ph.D. — Metallurgical & Materials Engineering (IIT Ropar) & Ambient Intelligence and Smart Systems (CCU)
Thesis: AI-Driven Approaches in Materials and Manufacturing for Quality Control and Monitoring (AIM²-QC)
2018–2020
M.Tech — Nanotechnology
Central University of Jharkhand, India
2011–2015
B.E. — Mechanical Engineering
University of Pune, India
Research

Research Pillars

Our work spans the complete lifecycle of intelligent products and manufacturing systems — from design and production to quality inspection, predictive maintenance, optimization, and autonomous orchestration.

X: Intelligent Manufacturing

AI-driven systems integrating machine learning, process optimization, quality control, predictive maintenance, and autonomous production for Industry 5.0.

X: Physical AI

Intelligent machines that perceive, reason, and interact with the physical world through robotics, sensors, and autonomous decision-making.

X: Robotics & HRC

Robot vision, cognitive robotics, collaborative automation, and robotic quality inspection for smart industries.

X: Digital Twins

Synchronized physical–virtual systems for real-time monitoring, simulation, predictive analytics, and immersive decision support.

X: LLMs & Agentic AI

Autonomous agents and foundation models integrating domain knowledge with manufacturing intelligence for reasoning and planning.

X: Trustworthy AI

Explainable AI, AI governance, uncertainty quantification, safety, robustness, and transparency for engineering applications.

X: Physics-Informed AI

Physics-Informed Neural Networks (PINNs) and hybrid models for intelligent process prediction and control.

X: Sustainable & Green AI

Technologies that reduce energy consumption, optimize resources, and support environmentally sustainable manufacturing.

X: Semiconductor AI

AI for semiconductor design, yield optimization, and intelligent analog & mixed-signal circuit design.

Choose Your X. Follow Your DIL.

At DIL-X, we do not define your future — we provide the environment to discover it. Every research challenge is an opportunity to define a new X, and every breakthrough begins with curiosity, scientific excellence, and a commitment to serving humanity.

Human-Centered AI Computer Vision Edge Intelligence Smart Cities Intelligent Healthcare Multimodal AI Foundation Models The X of Your Choice
● NSTC Funded Project · Principal Investigator

PINN-FM — A Physics-Informed Foundation Model for Machining

A National Science and Technology Council (NSTC) funded project led by Dr. Ayush Pratap, developing the next generation of AI foundation models for intelligent manufacturing.

🏛 NSTC, Taiwan 👤 PI: Dr. Ayush Pratap 📅 From August 2026 ⚙ Machining · Industry 5.0

“PINN-FM: Development of a Physics-Informed Neural Network-Based Foundation Model for Machining Industry Orchestration.” The project unifies physics-informed and agentic AI into a single foundation model for machine-tool autonomy — enabling real-time monitoring, adaptive control, and sustainable process optimization.

  • Physics-informed and agentic AI for tool-condition assessment, defect detection, and parameter prediction.
  • Multimodal learning across power, thermal, acoustic, vibration, and image data from machining experiments.
  • Chain-of-thought reasoning, RAG, and multi-agent orchestration for autonomous machine-tool decision support.
  • A unified “Large X Model” foundation model — the PINN-FM — for real-time, sustainable machining orchestration.
Co-Principal Investigators
We're Hiring

The PINN-FM project is recruiting motivated researchers to join DIL-X. Funded positions are available:

Ph.D. PositionsPhysics-informed & agentic AI for manufacturing
Master's PositionsThesis research across the project's core areas
✉ Apply — email your CV & interests
PINN-FM graphical abstract — plan, proof of concept, model evolution, integration, and goal
PINN-FM graphical abstract — from multimodal machining data to a unified physics-informed foundation model.
Recognition

Honours & Awards

Recognition of contributions to Artificial Intelligence, Manufacturing, and Automation.

2026 · PI

NSTC Project Grant

Principal Investigator on “PINN-FM: A Physics-Informed Neural Network-Based Foundation Model for Machining Industry Orchestration.”

2025

Best Paper Award

International Symposium on Computer, Consumer and Control (IS3C), Taichung, Taiwan.

2024

Third Prize — National Innovation & Entrepreneurship Competition

Prestigious national competition, Taiwan.

Taiwan

Overseas Research Fellowship (Level A)

Awarded by the Government of Taiwan.

Taiwan

NSTC Project Fellowship

National Science and Technology Council, Taiwan.

2024

Founder — OptiMOS.AI

AI-assisted semiconductor design startup, incubated at Startup Land, CCU.

Selected Publications

Research Output

Published in NDT & E International, Information Fusion, Journal of Materials Research, Advanced Engineering Materials, IEEE Technology & Society Magazine, Int. J. of Advanced Manufacturing Technology, and more.

1
A. Pratap, N. Sardana, T. Wu, P. Karthikeyan, P.-A. Hsiung, “Revolutionizing NDT 4.0 with Deep Attention Learning for Anomaly Detection (DAL-AD) in Mg-based L-PBF components,” NDT & E International, Vol. 158, 2026.
2
S. Utomo, A. Pratap, et al., “When explainable AI meets data governance: Enhancing trustworthiness in multimodal gas classification,” Information Fusion, Vol. 125, 2026.
3
A. Pratap, P.-A. Hsiung, N. Sardana, “TMRF: Trustworthy Microstructure Recognition Framework with Deep Learning and Explainable AI,” Journal of Materials Research, Vol. 40(6), 2025.
4
N. M. Eldabah, A. Pratap, et al., “Design Approaches of High-Entropy Alloys Using Artificial Intelligence: A Review,” Advanced Engineering Materials, Vol. 27(12), 2025.
5
A. Pratap, T.-K. Vi, Y. W. Lee, N. Sardana, P.-A. Hsiung, Y.-C. Kao, “A DT framework integrating human and artificial intelligence for power consumption prediction in CNC machining,” Int. J. of Advanced Manufacturing Technology, Vol. 135(1), 2024.
6
P. Karthikeyan, A. Pratap, W. C.-H. Chu, P.-A. Hsiung, “Analysis of Fisherman Exploitation in Taiwan Distant Water Fishing,” IEEE Technology and Society Magazine, Vol. 42(3), 2023.
7
A. Pratap, N. Sardana, S. Utomo, et al., “A synergic approach of deep learning towards digital additive manufacturing: A review,” Algorithms, Vol. 15(12), 2022.
8
A. Pratap, et al., “Deep Learning Technology in Genomics, Radiotherapy and Ophthalmology for Precision Medicine,” Journal of Physiological Investigation, 2026 Accepted
9
A. Pratap, I-H. Wang, W. L. Chang, S.-Y. Chen, Y.-C. Kao, “Development of a Power Consumption Prediction System for Contour Milling,” CIRP Journal of Manufacturing Science and Technology Accepted
1
A. Pratap, N. Sharma, N. Sardana, P.-A. Hsiung, “Harnessing Large Language Models for Sustainable Materials and Manufacturing,” IS3C 2025, Taichung, Taiwan. Best Paper Award
2
S. Raoruja, P. P.-Wei, Y.-W. Miao, A. Pratap, N. J. Ou, Y.-C. Kao, “Bridging Physical and Virtual Robotics: Real-Time Digital Twin with Vision-Based Identification,” Int. Conf. on Automation Technology (Automation), 2025.
3
N. Sharma, A. Pratap, P.-A. Hsiung, “Intelligent Analog and Mixed-Signal IC Design: A Conceptual Framework and Case Study on AI Integration,” IS3C 2025, Taiwan.
4
A. Pratap, N. Sharma, T. Wu, P. Karthikeyan, N. Sardana, P.-A. Hsiung, “SegMAgNet: A Comparative Study of Segmentation Models for Defect Detection in Additively Manufactured Mg Alloys,” IEEE AVSS 2025, Tainan, Taiwan.
5
A. Pratap, N. Sardana, “Explaining the Identification of Granular Crack with Deep Learning and XAI,” IEEE TENSYMP 2024.
6
A. Pratap, N. Sardana, S. Utomo, A. John, P. Karthikeyan, P.-A. Hsiung, “Analysis of defect associated with powder bed fusion with deep learning and explainable AI,” IEEE KST 2023.
7
A. Pratap, N. Sardana, “Machine learning-based image processing in materials science and engineering: A review,” Materials Today: Proceedings, Vol. 62, 2022.
1
A. Pratap, A. Pandey, N. Sardana, “Machine learning and additive manufacturing: A case study for quality control and monitoring,” in Modern Materials and Manufacturing Techniques, CRC Press, 2024.
2
A. Pratap, N. Sardana, “Advancement of machine learning and image processing in material science,” in Modern Materials and Manufacturing Techniques, CRC Press, 2024.
3
Indian Patent — “MOSS Basin,” A. Pratap, N. Sardana. Application No. 202511070138 Submitted
Get in Touch

Join DIL-X · Contact

We welcome curious, purpose-driven researchers. Choose your X and pursue it with us.

🏛
Institution
National Chung Cheng University (CCU)
📍
Address
168 University Road, Ming-Hsiung Township,
Chia-Yi 621, Taiwan, R.O.C.
🎓
in
LinkedIn
ayush-pratap

Opportunities

DIL-X welcomes collaboration and new members across all levels:

To choose your X, a proper project proposal is welcome. Reach out by email to begin the conversation.