Automatic Patrol and Inspection Method for Machinery Diagnosis Robot—Sound Signal-Based Fuzzy Search Approach

摘要

This paper developed the basic theories and techniques for a plant machinery diagnosis robot (MDR). The workplace of MDR is usually a large-scale plant or a place with a dangerous environment. It must autonomously carry out the condition monitoring of plant machinery with sensors in order to detect machinery faults for securing the safety of the plant. In this paper, the basic function, concept and structure of the MDR are discussed. The intelligent control method by rough set, fuzzy neural network (FNN) and self-location-azimuth correction for the MDR that patrols on the inspection route are proposed. Additionally, navigation and search method by fuzzy inference using extracted fault sound signals are also proposed, by which the MDR will be navigated to the near side of the faulty machine when the fault of a machine has been detected during inspection. Finally, examples of practical navigation and fault machine searching are also shown.