Methodological Approach for Virtual Sensors design using Artificial Neural
Professor Francklin Rivas-Echeverria
Universidad de Los Andes
Laboratorio de Sistemas Inteligentes
Abstract: Virtual sensors constitute a novel area of virtual
instrumentation, whose principal mission is to perform indirect measurements
of process important variables using historical data of the desired variable
and some other variable that affects its performance.
Virtual sensors are some times designed for working in parallel with a
physical sensor in order to evaluate its performance, but they can also be
used for having on-line estimation of the desired measurement.
Virtual sensors are widely used because they are computer programs that can
be change or updated when it is necessary. These programs can consist of a
mathematical model, heuristic models or intelligent model.
Neural networks have been one of the most used intelligent tool for
designing and developing Virtual Sensors due to its accurate, its capability
for identifying complex nonlinear dynamical systems, giving appropriate
results in different situations, modeling and Identification capabilities
and easy for implantation.
This plenary will present some methodological frameworks for designing
Virtual Sensors using Artificial Neural Networks. This Methodology is based
upon Software Engineering, Knowledge-Based Systems and Neural Networks
schemes. It includes both technical and economical feasibility for building
the virtual sensors and considers important aspects concerning computational
platform, data processing, virtual sensor requirements, among others. It
also considers the computational nature of virtual sensors.
It will be also presented some industrial examples.
Brief Biography of the Speaker:
Francklin Rivas-Echeverria Systems Engineer, MSc. in Control Engineering and
Applied Science Doctor. Full professor in Control Systems Department, at
Universidad de Los Andes, Venezuela. He has been invited professor in the
Laboratoire d'Architecture et d'Analyse des Systemes (LAAS, Toulouse-France)
and some Venezuelan and international Universities. He has also been
technical advisor for “Venezuelan Oil Company” (PDVSA), “Aluminum Venezuelan
Company” (VENALUM), “Steel Venezuelan Company” (SIDOR), Trolleybus System in
Venezuela (TROLMERIDA). He has created and is the Director of the
Intelligent Systems Laboratory and is the head of the University consulting
unit (UAPIT-ULA). Over 180 publications in high level conferences and
journals: the main topics of his papers are: Artificial Intelligence,
Intelligent Control, Automation Systems and Industrial Applications. He has
applied his results to many fields: Processes Control and Supervision, Oil
production, Steel production processes, among others. Also, has developed
several tools for automatic control teaching. He is coauthor of two books
concerning Artificial Intelligence and Nonlinear Systems.