Current Research

National Science Foundation (NSF): US Turkey Cooperative Research: Application of VLSI Based Soft Computing to Mechatronics

Principal Investigator: Bogdan (Dan) M. Wilamowski

Research Assistants:

Duration: 9/1/00 to 7/31/02

Application of VLSI based soft computing to mechatronics: The twentieth century has witnessed a widespread of innovations in both the hardware and software design. In the first half of the century, the emphasis was mainly on the development of an accurate mechanical component design, whereas in the second half, new technologies emerged together with new needs and new directions in industry. A natural consequence of this rapid growth is the emergence of the field of intelligent systems. Conceptually, the degree of intelligence is closely related to the design methodology followed. The limits of the intelligent behavior are determined by the flexibility of the architecture, the ability to realize the human expertise, laws of inference procedure and the speed of learning. All of these titles are the main constituents of the research area named Soft Computing. Soft computing is a practical alternative for solving complex problems through the use of human expertise and prior knowledge about the problem in hand. The main subtitles of the area are artifcial neural networks and fuzzy inference systems.

Artificial Neural Networks are well known with their property of representing complex nonlinear mappings. Earlier works on the mapping properties of these architectures have shown that neural networks are universal approximators. The mathematical power of intelligence is commonly attributed to the neural systems because of their massively interconnected fault tolerant architecture.

Fuzzy Inference Systems are the most popular constituent of the soft computing area since they are able to represent human expertise in the form of IF-THEN statements. In this domain, the system behavior is modeled through the use of linguistic descriptions.

A successful application area of soft computing techniques is Mechatronics. The work 'mechatronics' stands for a synergistic integration of mechanical and electronic subsystems with intelligent computer control. As the name itself implies, the area is an interdisciplinary research field including electronics, mechanical, industrial, and computer science engineering expertise. The typical examples of mechatronic systems are robotic manipulators, washing machines, camera systems and sewing machines. In such products or systems, mechanical and electronic parts are combined and the resulting system is controlled by embedded software.

Current Research