Dynamics & Design Conference
Online ISSN : 2424-2993
2017
セッションID: 505
会議情報

群知能を用いた振動監視システムが認識する振動モードについて
*樋浦 琢也森下 信
著者情報
会議録・要旨集 フリー

詳細
抄録

The swarm intelligence has been applied to a mechanical vibration monitoring system for the perfect autonomous computer monitoring system including sensors, actuators and adaptive controllers. The expression of "swarm intelligence" was first used in 1988 in the context of cellular robotic systems, where lots of simple agents may generate self-organized patterns through mutual interactions. As an example, a swarm of ants can find an optimal route between their nest and the food in various environment using special pheromone. In this sense, the network of agents in a swarm may have some kind of intelligence or higher function appeared in a simple agent, which is defined as the swarm intelligence. The concept of swarm intelligence may be applied in diverse engineering fields such as flexible pattern recognition, adaptive control system, or intelligent monitoring system, because some kind of intelligence may emerge on the network without any special control system. In this study, a number of units composed of a sensor and an actuator were distributed on a mechanical dynamic system, and each unit was connected to each other to exchange the information of state variables sensed by each unit. The network of units configured as a mutual connected neural network. A lumped mass system with five degree-of-freedom was prepared as the mechanical system in this simulation, and each unit was placed on each lumped mass. The displacement was measured by the sensor in each unit, and a variable damper was assumed as actuator in each unit. After the several expected vibration-controlled patterns of lumped system were memorized by pattern recognition procedure in mutual connected neural network, then the excited vibration mode was inhibited to the memorized patterns automatically. The result showed that the excited vibration was reduced autonomously by the swarm intelligence configured on the network of units distributed on a mechanical system.

著者関連情報
© 2017 一般社団法人 日本機械学会
前の記事 次の記事
feedback
Top