Abstract

This article shows a pattern recognition method for object classification using ultrasonic sensors and a dual knowledge base fuzzy expert system. The developed system uses a pair of ultrasonic sensors for obtaining information about the object shape from the ultrasonic echo signal envelope. In order to reduce the size of the database, a set of parameters is calculated for extracting knowledge about the object. However, the information provided by ultrasonic sensors contains a very high uncertainty level. This uncertainty is caused by several environmental effects, which are very difficult to eliminate in industrial applications. Among these environment factors are the air temperature and humidity, the air movement, etc. They create variations in the proprieties of the medium and disturbances during the acoustic propagation process. The presented system has been specially designed for industrial applications, where it is very difficult to reduce these disturbances and where it is necessary to use intelligent systems with high autonomy. The fuzzy expert system proposed has a dual knowledge base, that is, a statistical knowledge located on the memberships functions, and the standard rule-based knowledge. This expert system deals with the uncertainties in the information, and it is able to generate and modify the knowledge base and the decision rules in an automatic way. Furthermore, it is able to adapt the knowledge base to the slow changes produced by disturbing factors, such as humidity and temperature. On the other hand, because this system maintains a rule-based structure it is very easy to incorporate expert human knowledge.

Author Keywords: Fuzzy expert systems; Pattern recognition; Ultrasounds; Uncertainty

Article Outline

1. Introduction

2. Experiment design

3. Features extraction from the ultrasonic echo

4. Features selection

5. Proposed fuzzy expert system

5.1. Membership functions

5.2. Rules system

5.3. Decision subsystem

6. Experimental results

7. Conclusions

Acknowledgements

References

Corresponding author. Tel.: +34-942-201542; fax: +34-942-201873; email: llata@teisa.unican.es