Abstract
The purpose of this study is to develop the basic theories and techniques for a plant inspection and diagnosis robot. The robot dealt with in this study will works in the large scale unmanned plant or a place with dangerous equipment. It has the ability widely to monitor the condition of plant machinery with only a few sensors, and quickly to discrimimate machine failures, in order to guarantee both the quality and quantity of production against accident. In this paper, the conceptual design and the method of failure detection by sound information for a plant inspection and diagnosis robot are discussed, including following contents : (1) the basic function and structure of the plant inspection and diagnosis robot, (2) the calculation method of symptom parameters from sound signal for detection and diagnosis of machine failures, (3) the method of making membership functions of the symptom parameters by possibility measure theory, (4) the method of failure discrimination by the membership functions, (5) examples of practical inspection and diagnosis.
