Introduction
With the development of
information sciences and technologies, practical processes, such as chemical
industry, metallurgy, machinery, electronics, transportation, and logistics,
pose enormous research and technical challenges for control engineering and
management due to their size, distributed and multi-domain nature, safety and
quality requirements, complex dynamics and performance evaluation, maintenance
and diagnosis. Modeling these processes accurately using first principles or
identification is almost impossible although these plants produce and store
huge amount of impersonal valuable data on the plant and equipment operations
in every moment during production. This challenges the existing control theory
and technology, and meanwhile urgently pushes scientists and engineers to
develop new data driven control and methodology to solve control and
optimization issues for these complex practical plants. The high-tech
hard/software and the cloud computing enable us to have ability to perform a
complex computation real time, which makes the implementation of data driven
control and methodology in practice possible. Thus, it would be very
significant if we can learning the systems’ behaviors, discovering the
correlation relationship of system variables by making full use of those
on-line or off-line process data, to directly design controller, predict and
assess system states, evaluate performance, make decisions, perform real-time
optimization, and conduct fault diagnosis. For this reason, the establishment
and development of datadriven control theory and methodology are urgent issues
in both the theory and applications.
This Special Section is
to provide a forum for researchers and practitioners to exchange their latest achievements
and to identify critical points and challenges for future investigation on
modeling, control and learning of complex practical systems in a data driven
manner. The papers to be published in this issue are expected to provide latest
advances of data driven approaches, particularly the novel theoretical-supported
ideas and algorithms with practical applications.
Topics
Topics include, but are
not limited to, the following research areas:
4 Model-free or data-driven
control approaches and applications
4 Data driven learning and
control approaches and applications
4 Data driven decisions,
performance evaluation, fault diagnosis, etc. and applications
4 Complementary controller
design approaches and applications between data driven and model based control
methods
4 Data driven modeling
approaches for complex industrial processes
4 Data driven optimization
methods and applications
4 Robustness on the data
driven control
4 Neural network and
reinforcement learning control and practical applications in model-free
environment.
Manuscript Preparation and Submission
Check carefully the style
of the journal described in the guidelines “Information for Authors” in the
IEEE- IES
web site: http://www.ieee-ies.org/index.php/pubs/ieee-transactions-on-industrial-electronics .
Please submit your
manuscript in electronic form through: https://mc.manuscriptcentral.com/tie-ieee/.
On the submitting page,
in pop-up menu of manuscript type, select: “SS on Data Driven Control
and Learning Systems”, then upload all your manuscript files
following the instructions given on the screen.
Corresponding Guest Editor
Prof. Zhongsheng Hou
School of Electronic and
Information Engineering
Beijing Jiaotong
University
Beijing, P. R. China
EMAIL: zhshhou@bjtu.edu.cn
Guest Editor
Prof. Huijun Gao
Research Institute of
Intelligent Control and Systems
Harbin Institute of
Technology
Harbin, P. R. China
EMAIL: hjgao@hit.edu.cn
Guest Editor
Prof. Frank L. Lewis
UTA Research Institute
University of Texas at
Arlington
Arlington, USA
EMAIL: Lewis@uta.edu
Special Section email: SSddcls@ieee-ies.org
Submission management email: tie-submissions@ieee-ies.org
Timetable
Deadline for manuscript submissions: February 29, 2016
Information about
manuscript acceptance: Summer, 2016
Publication date: Winter, 2016
|