Expensive models and experiments
PIML can reduce repeated simulation or experimental cost while retaining the governing knowledge used in Advanced Mechatronics and Industrial Automation.
Engineering Research Community
Advanced Mechatronics and Industrial Automation & Physics-Informed Machine Learning
Intelligent machines grounded in dynamics, sensing, control and industrial evidence
Advanced Mechatronics and Industrial Automation integrates mechanical systems, electronics, sensors, actuators, embedded computing, robotics, control, industrial communication and production engineering. Typical systems include robot manipulators, servo drives, CNC equipment, automated assembly lines, mobile robots, machine tools, smart actuators and cyber-physical production systems.
These systems generate abundant operational data but remain governed by dynamics, kinematics, circuit laws, actuator limits, contact mechanics, control constraints and safety requirements. PIML can combine those models with data to improve identification, prediction, monitoring and control.
This page presents ten focused research areas, degree-level project pathways, selected publications and direct support through the PIMLS biweekly members meeting.
This Advanced Mechatronics and Industrial Automation guide covers Physics-Informed Neural Networks (PINNs), physics-guided machine learning, scientific machine learning, neural operators, hybrid models and engineering digital twins. Explore the research and project pathways below, then join the Physics-Informed Machine Learning Society to connect with the international PIMLS community.
The central ideaMechatronic dynamics + industrial sensing and logic + safe machine learning
10focused research areas
3academic project pathways
6selected publications
Biweeklymember research meeting
Why this combination matters
Why Advanced Mechatronics and Industrial Automation Needs Physics-Informed Learning
Use available scientific knowledge to make limited data more useful, transparent and testable.
Incomplete engineering models
Learn uncertain parameters, closures or discrepancies around an inspectable mechanistic foundation.
Transfer across conditions
Test whether structured models generalize across geometries, materials, assets, operating regimes or sites.
Trustworthy evidence
Use physical residuals, independent measurements, uncertainty and conventional engineering baselines before deployment.
Ten focused directions
Major Advanced Mechatronics and Industrial Automation PIML Research Areas
Each card connects a meaningful Advanced Mechatronics and Industrial Automation question with suitable scientific knowledge, modelling choices and evidence needed to test it.
01
Robot Forward and Inverse Dynamics
PIML can estimate accelerations from states and torque, or infer torque required for a desired motion. Structure-preserving approaches may learn an energy, Lagrangian or Hamiltonian rather than an arbitrary state transition.
Model and evidenceGoverning equations, calibrated measurements and held-out operating conditions
02
Kinematics and Calibration
Geometric parameters, joint offsets, compliance and tool frames can be estimated from measurements while respecting the robot chain. This is useful for precision assembly, machining and metrology.
Model and evidenceMechanistic and data-only baselines, uncertainty and independent validation
03
Friction, Backlash and Hysteresis
These effects cause major model mismatch. A residual learner can correct a nominal model using direction, speed, load and temperature, while regularisation prevents unphysical corrections.
Model and evidenceGeometry, material or system parameters, sensor data and physical residuals
04
Flexible-Joint and Flexible-Link Robots
Lightweight systems and collaborative robots show compliance and vibration. Hybrid rigid–flexible models can combine beam/continuum mechanics, modal coordinates and measured motion.
Model and evidenceGoverning equations, calibrated measurements and held-out operating conditions
05
Soft Robotics
Soft robots have nonlinear material behaviour, distributed deformation and complex actuation. The cited dielectric-elastomer study demonstrates the value of learning uncertain material properties inside an analytical dynamics model. Continuum mechanics and constitutive laws provide useful priors.
Model and evidenceMechanistic and data-only baselines, uncertainty and independent validation
06
Pneumatic and Hydraulic Systems
Pressure–flow relations, valve dynamics, compressibility, leakage and friction interact. PINNs or grey-box neural ODEs can estimate hidden pressures, flows and uncertain coefficients from limited sensors.
Model and evidenceGeometry, material or system parameters, sensor data and physical residuals
07
Servo Motors and Drives
Electrical, magnetic, mechanical and thermal dynamics are coupled. PIML can estimate load torque, rotor temperature, friction or degradation while retaining motor equations and drive constraints.
Model and evidenceGoverning equations, calibrated measurements and held-out operating conditions
08
Machine Tools and CNC Systems
Potential uses include thermal-error compensation, chatter prediction, tool-wear estimation, contour-error modelling and feed-drive digital twins. Physics can enter through structural modes, cutting-force models, heat transfer and axis dynamics.
Model and evidenceMechanistic and data-only baselines, uncertainty and independent validation
09
Industrial-Robot Degradation
The 2025 *Mechanical Systems and Signal Processing* study on robot reducer degradation embedded robot dynamics and servo-controller knowledge into a multi-physics-informed network for motor-current and remaining-life assessment. DOI: https://doi.org/10.1016/j.ymssp.2025.112793 This is an especially relevant…
Model and evidenceGeometry, material or system parameters, sensor data and physical residuals
10
Predictive Maintenance
Physics-guided health indicators can be formed from energy loss, vibration modes, torque residuals, thermal balance or wear laws. Remaining-useful-life models should represent uncertainty and should be tested on run-to-failure or genuinely held-out degradation trajectories.
Model and evidenceGoverning equations, calibrated measurements and held-out operating conditions
Choose the right research depth
Projects for Every Academic Stage
Start with a scope that matches your time, mathematical background, experimental access and expected research contribution.
Project pathway 1
B.E./B.Tech
Learn the foundations with a bounded, measurable system.
- Physics-informed DC motor parameter estimation.
- Two-link robot dynamics learning.
- Pneumatic-cylinder pressure/state reconstruction.
- Energy-aware anomaly detection for a conveyor.
- Thermal-error prediction for a small CNC axis.
Expected outcome
A reproducible implementation, clear baselines, a manageable dataset and physically meaningful validation.
Project pathway 2
M.Tech
Combine an engineering model, substantial data and rigorous comparison.
- Residual friction learning for precision tracking.
- Robot-joint digital twin with current and vibration data.
- Physics-guided gearbox degradation indicator.
- Hybrid soft-actuator modelling.
- Safe MPC using a learned constrained dynamics model.
Expected outcome
A thesis-quality study with held-out regimes, mechanistic and data-only baselines, ablation and uncertainty.
Project pathway 3
Ph.D.
Address a publishable methodological, multiscale or deployment research gap.
- Uncertainty-aware robot degradation and maintenance decisions.
- Structure-preserving learning for flexible robots.
- Multi-fidelity industrial-cell digital twins.
- Physics-informed contact learning for collaborative robots.
- Certified or verifiably safe adaptive control.
Expected outcome
New methodology or validated engineering insight, multi-regime evidence, reproducible software and journal publications.
From idea to evidence
A Strong PIML Project Workflow
01
Define
Choose one Advanced Mechatronics and Industrial Automation question and a measurable engineering output.
02
Model
State the governing relationships, constraints or validated domain knowledge you will retain.
03
Compare
Build mechanistic and data-only baselines before the hybrid model.
04
Validate
Hold out experiments, conditions, assets, sites or regimes at the deployment level.
05
Publish
Report uncertainty, ablation, limitations, data lineage and reproducible code.
Read before you modelDiscuss Your Literature
Selected Publications and Why They Matter
Use this focused reading list to understand the general PIML framework, direct Advanced Mechatronics and Industrial Automation evidence and suitable hybrid modelling methods.
Literature review advice
Do not list papers only. Compare the engineering question, incorporated knowledge, data, split strategy, baselines, uncertainty and evidence level.
This source is included in the Advanced Mechatronics and Industrial Automation literature guide because it demonstrates or reviews a relevant physics-informed, hybrid, inverse, surrogate or scientific-machine-learning approach. Read the methods, data split, baselines and validation evidence—not only the reported accuracy.
How to use this paper: Use this paper to refine the research question, identify a defensible physical prior and compare evidence requirements for Advanced Mechatronics and Industrial Automation.
Read publication or record This source is included in the Advanced Mechatronics and Industrial Automation literature guide because it demonstrates or reviews a relevant physics-informed, hybrid, inverse, surrogate or scientific-machine-learning approach. Read the methods, data split, baselines and validation evidence—not only the reported accuracy.
How to use this paper: Use this paper to refine the research question, identify a defensible physical prior and compare evidence requirements for Advanced Mechatronics and Industrial Automation.
Read publication or record This source is included in the Advanced Mechatronics and Industrial Automation literature guide because it demonstrates or reviews a relevant physics-informed, hybrid, inverse, surrogate or scientific-machine-learning approach. Read the methods, data split, baselines and validation evidence—not only the reported accuracy.
How to use this paper: Use this paper to refine the research question, identify a defensible physical prior and compare evidence requirements for Advanced Mechatronics and Industrial Automation.
Read publication or record This source is included in the Advanced Mechatronics and Industrial Automation literature guide because it demonstrates or reviews a relevant physics-informed, hybrid, inverse, surrogate or scientific-machine-learning approach. Read the methods, data split, baselines and validation evidence—not only the reported accuracy.
How to use this paper: Use this paper to refine the research question, identify a defensible physical prior and compare evidence requirements for Advanced Mechatronics and Industrial Automation.
Read publication or record This source is included in the Advanced Mechatronics and Industrial Automation literature guide because it demonstrates or reviews a relevant physics-informed, hybrid, inverse, surrogate or scientific-machine-learning approach. Read the methods, data split, baselines and validation evidence—not only the reported accuracy.
How to use this paper: Use this paper to refine the research question, identify a defensible physical prior and compare evidence requirements for Advanced Mechatronics and Industrial Automation.
Read publication or record This source is included in the Advanced Mechatronics and Industrial Automation literature guide because it demonstrates or reviews a relevant physics-informed, hybrid, inverse, surrogate or scientific-machine-learning approach. Read the methods, data split, baselines and validation evidence—not only the reported accuracy.
How to use this paper: Use this paper to refine the research question, identify a defensible physical prior and compare evidence requirements for Advanced Mechatronics and Industrial Automation.
Read publication or record Build an interdisciplinary team
Where Advanced Mechatronics and Industrial Automation Can Collaborate
Mechanical Engineering
Dynamics, mechanisms, vibration and tribology.
Electrical Engineering
Drives, power electronics and sensing.
Computer Science
Real-time software, edge AI and learning algorithms.
Manufacturing
Process monitoring, quality and production integration.
Before you begin
Frequently Asked Research Questions
These answers help students avoid common scope, terminology and validation mistakes.
Still have a question?
Use the biweekly meeting form for research guidance.
Request accessNo. Advanced Mechatronics and Industrial Automation projects may use physics-guided features, hybrid residual models, differentiable simulators, neural operators, constrained architectures or data assimilation. State exactly what knowledge is incorporated.
Choose one engineering question, a measurable output and a defensible mechanistic baseline. Add learning only where data can identify an uncertainty or discrepancy.
A meaningful question, justified prior knowledge, deployment-level holdouts, strong baselines, ablation, uncertainty, reproducibility and honest limitations.
Simulation can broaden coverage, but simulation-only evidence cannot establish real-system accuracy. Use calibrated experiments, field measurements or trusted independent references appropriate to the claim.
Submit the biweekly members meeting form to discuss your project level, branch, data, model, validation plan and possible collaborators.
Take the next step
Bring your Advanced Mechatronics and Industrial Automation research idea to PIMLS
Join the biweekly members meeting for project guidance, collaboration and publication planning—or contact the Society directly.
Meeting participation is requested through the Google form. Complete it carefully so the Society can understand your research interest.