Special Issue on Data-Driven Modeling and Control of Dynamical Systems
The field of dynamical systems has undergone a revolutionary transformation due to advances in data-driven modeling and control techniques. These advancements have brought about significant breakthroughs across diverse domains, including engineering, robotics, finance, biology, and environmental sciences. The utilization of these approaches has enabled capturing complex dynamics, adaptability to changing conditions, exploitation of real-world data, enhancement of accuracy, reduction of modeling effort, integration of domain knowledge, and facilitation of rapid prototyping. As data-driven methods continue to evolve, their potential impact is expected to expand further, driving further innovation, enabling more efficient processes, and fostering performance improvements in diverse applications.
However, it is crucial to acknowledge the existing limitations of data-driven approaches, such as the availability and quality of data, limited generalization capabilities, lack of physical interpretability, and absence of theoretical guarantees. Researchers are actively working on overcoming these shortcomings by incorporating physics-based priors into learning algorithms, ensuring interpretability of the learned models, and establishing theoretical guarantees for learning-based estimation and control. These endeavors aim to strengthen the foundations of data-driven methods and enhance their reliability, interpretability, and applicability in real-world scenarios. By addressing these challenges and building upon recent advancements, data-driven modeling and control techniques are poised to play a transformative role in various fields, continuing to shape the way we understand, analyze, and manipulate dynamical systems, fueling progress, and driving innovation across industries.
This special issue will provide readers with the latest research advancements in utilizing data-driven methods for modeling, learning, and control.
Topic AreasTHE SCOPE OF THIS ISSUE INCLUDES BUT IS NOT LIMITED TO:
- Machine learning and data-driven techniques for modeling dynamical systems
- Deep learning approaches for modeling and control
- Identification and parameter estimation of dynamical systems
- Nonlinear system identification and control
- Model order reduction and system approximation techniques
- Reinforcement learning and optimal control of dynamical systems
- Data-driven control of complex and large-scale systems
- Real-time and online learning algorithms for control
- Applications of data-driven modeling and control in engineering, biology, finance, robotics, aerospace, flow control, and other domains
Submission InstructionsPapers should be submitted electronically to the journal through the ASME Journal Tool. If you already have an account, log in as an author and select Submit Paper. If you do not have an account, you can create one here.
Once at the Paper Submittal page, select the Journal of Dynamic Systems, Measurement, and Control, and then under the Special Issue field, select Special Issue on Data-Driven Modeling and Control of Dynamical Systems.
Papers received after the deadline or papers not selected for the Special Issue may be accepted for publication in a regular issue.
Efstathios Bakolas: Department of Aerospace Engineering and Engineering Mechanics, The University of Texas at Austin (email@example.com)
Suman Chakravorty: Department of Aerospace Engineering, Texas A&M University (firstname.lastname@example.org)
Santosh Devasia: Department of Mechanical Engineering, University of Washington (email@example.com)
Vaibhav Srivastava: Department of Electrical and Computer Engineering, Michigan State University (firstname.lastname@example.org)